Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 679 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.6149. Min Act: -0.1700
Data Index: 868121 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.4587. Min Act: -0.1700
Data Index: 2484945 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.3962. Min Act: -0.1700
Data Index: 4486274 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.3962. Min Act: -0.1700
Data Index: 1353118 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.3962. Min Act: -0.1700
Data Index: 3008231 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.3649. Min Act: -0.1700
Data Index: 4557866 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.3024. Min Act: -0.1700
Data Index: 5055653 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.3024. Min Act: -0.1700
Data Index: 5913302 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2712. Min Act: -0.1700
Data Index: 8608043 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2399. Min Act: -0.1700
Data Index: 6035400 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2399. Min Act: -0.1700
Data Index: 716404 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2399. Min Act: -0.1700
Data Index: 8660445 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2399. Min Act: -0.1700
Data Index: 1723117 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2399. Min Act: -0.1700
Data Index: 4687605 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2399. Min Act: -0.1700
Data Index: 8660444 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2399. Min Act: -0.1700
Data Index: 8270171 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2087. Min Act: -0.1700
Data Index: 3277821 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2399. Min Act: -0.1700
Data Index: 5574061 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.2087. Min Act: -0.1700
Data Index: 8471068 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6149. Min Range: -4.6149
Max Act: 4.1774. Min Act: -0.1700
Data Index: 4267285 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19