Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2560 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.7193. Min Act: -0.1700
Data Index: 961091 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.5631. Min Act: -0.1700
Data Index: 7431966 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.3756. Min Act: -0.1700
Data Index: 627895 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.2506. Min Act: -0.1700
Data Index: 8466987 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.2506. Min Act: -0.1700
Data Index: 8382287 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.2506. Min Act: -0.1700
Data Index: 2538492 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.1881. Min Act: -0.1700
Data Index: 1228913 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.1881. Min Act: -0.1700
Data Index: 2598917 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.1881. Min Act: -0.1700
Data Index: 1387649 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.1568. Min Act: -0.1700
Data Index: 6736946 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.1568. Min Act: -0.1700
Data Index: 8257941 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.1881. Min Act: -0.1700
Data Index: 6563743 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.0631. Min Act: -0.1700
Data Index: 7506912 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.0631. Min Act: -0.1700
Data Index: 4523160 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.0631. Min Act: -0.1700
Data Index: 3623223 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.0318. Min Act: -0.1700
Data Index: 1965934 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.0318. Min Act: -0.1700
Data Index: 7479259 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.0631. Min Act: -0.1700
Data Index: 3377088 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.0006. Min Act: -0.1700
Data Index: 603986 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7193. Min Range: -5.7193
Max Act: 5.0006. Min Act: -0.1700
Data Index: 4591800 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19