Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1636 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.5748. Min Act: -0.1700
Data Index: 3779400 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.5748. Min Act: -0.1700
Data Index: 696288 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.5748. Min Act: -0.1700
Data Index: 3519438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.3248. Min Act: -0.1700
Data Index: 1169851 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.2623. Min Act: -0.1700
Data Index: 3635380 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.2310. Min Act: -0.1700
Data Index: 5761744 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.1998. Min Act: -0.1700
Data Index: 2350730 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.1998. Min Act: -0.1700
Data Index: 8456829 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.1998. Min Act: -0.1700
Data Index: 8349257 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.1685. Min Act: -0.1700
Data Index: 4311314 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.1373. Min Act: -0.1700
Data Index: 4164992 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.1373. Min Act: -0.1700
Data Index: 654045 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.1060. Min Act: -0.1700
Data Index: 2429351 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.0748. Min Act: -0.1700
Data Index: 8164382 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.1060. Min Act: -0.1700
Data Index: 1691478 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.1060. Min Act: -0.1700
Data Index: 3183308 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.0435. Min Act: -0.1700
Data Index: 3336998 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.0748. Min Act: -0.1700
Data Index: 6054361 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.0748. Min Act: -0.1700
Data Index: 8790131 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5748. Min Range: -4.5748
Max Act: 4.0748. Min Act: -0.1700
Data Index: 3635379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19