Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 107 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.9825. Min Act: -0.1700
Data Index: 1402564 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.9200. Min Act: -0.1700
Data Index: 6315656 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.8574. Min Act: -0.1700
Data Index: 8007613 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.8418. Min Act: -0.1700
Data Index: 4259127 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.8262. Min Act: -0.1700
Data Index: 7618764 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.8105. Min Act: -0.1700
Data Index: 5937091 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.8105. Min Act: -0.1700
Data Index: 3180119 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.7949. Min Act: -0.1700
Data Index: 2242874 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.8105. Min Act: -0.1700
Data Index: 2916634 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.7793. Min Act: -0.1700
Data Index: 5614323 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.7636. Min Act: -0.1700
Data Index: 2488918 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.7636. Min Act: -0.1700
Data Index: 6782646 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.7480. Min Act: -0.1700
Data Index: 3154260 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.7480. Min Act: -0.1700
Data Index: 7978197 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.7167. Min Act: -0.1700
Data Index: 4613726 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.7323. Min Act: -0.1700
Data Index: 7890990 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.7167. Min Act: -0.1700
Data Index: 91908 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.6854. Min Act: -0.1700
Data Index: 7707928 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.6854. Min Act: -0.1700
Data Index: 7751235 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9825. Min Range: -3.9825
Max Act: 3.6854. Min Act: -0.1700
Data Index: 1430305 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19