Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1973 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.7562. Min Act: -0.1700
Data Index: 4009250 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.7250. Min Act: -0.1700
Data Index: 6010013 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.6000. Min Act: -0.1700
Data Index: 5679887 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.5375. Min Act: -0.1700
Data Index: 737407 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.4750. Min Act: -0.1700
Data Index: 685473 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.3187. Min Act: -0.1700
Data Index: 945970 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.2875. Min Act: -0.1700
Data Index: 2253346 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.3187. Min Act: -0.1700
Data Index: 8749377 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.2875. Min Act: -0.1700
Data Index: 5483346 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.2562. Min Act: -0.1700
Data Index: 174628 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.2250. Min Act: -0.1700
Data Index: 6859005 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.1937. Min Act: -0.1700
Data Index: 7859062 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.2562. Min Act: -0.1700
Data Index: 4501765 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.2562. Min Act: -0.1700
Data Index: 2133283 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.1937. Min Act: -0.1700
Data Index: 1979447 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.1937. Min Act: -0.1700
Data Index: 6623875 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.1625. Min Act: -0.1700
Data Index: 2363127 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.1312. Min Act: -0.1700
Data Index: 6735049 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.1312. Min Act: -0.1700
Data Index: 442763 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7562. Min Range: -6.7562
Max Act: 6.1625. Min Act: -0.1700
Data Index: 5334979 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19