Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5056 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 18.0431. Min Range: -18.0431
Max Act: 18.0431. Min Act: -0.1700
Data Index: 8276412 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.0431. Min Range: -18.0431
Max Act: 17.9181. Min Act: -0.1700
Data Index: 2266444 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.0431. Min Range: -18.0431
Max Act: 17.4181. Min Act: -0.1700
Data Index: 1406742 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.0431. Min Range: -18.0431
Max Act: 17.4181. Min Act: -0.1700
Data Index: 4700825 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.0431. Min Range: -18.0431
Max Act: 17.1681. Min Act: -0.1700
Data Index: 1087655 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.9181. Min Act: -0.1700
Data Index: 5987952 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.0431. Min Range: -18.0431
Max Act: 17.0431. Min Act: -0.1700
Data Index: 4958428 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.0431. Min Range: -18.0431
Max Act: 17.0431. Min Act: -0.1700
Data Index: 20169 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.0431. Min Range: -18.0431
Max Act: 17.0431. Min Act: -0.1700
Data Index: 2261225 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.9181. Min Act: -0.1700
Data Index: 8267348 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.9181. Min Act: -0.1700
Data Index: 7503504 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.9181. Min Act: -0.1700
Data Index: 5826848 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.9181. Min Act: -0.1700
Data Index: 8734190 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.9181. Min Act: -0.1700
Data Index: 7109806 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.9181. Min Act: -0.1700
Data Index: 2496053 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.7931. Min Act: -0.1700
Data Index: 5763361 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.7931. Min Act: -0.1700
Data Index: 6652981 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.7931. Min Act: -0.1700
Data Index: 2770228 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.7931. Min Act: -0.1700
Data Index: 7088518 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.0431. Min Range: -18.0431
Max Act: 16.7931. Min Act: -0.1700
Data Index: 7093204 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19