Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4501 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.7125. Min Act: -0.1700
Data Index: 6833157 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.7125. Min Act: -0.1700
Data Index: 6074809 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.5875. Min Act: -0.1700
Data Index: 5608536 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.6188. Min Act: -0.1700
Data Index: 3492095 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.5875. Min Act: -0.1700
Data Index: 779897 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.5563. Min Act: -0.1700
Data Index: 4362322 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.5250. Min Act: -0.1700
Data Index: 4517641 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.5250. Min Act: -0.1700
Data Index: 3430606 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.5250. Min Act: -0.1700
Data Index: 2380133 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.5250. Min Act: -0.1700
Data Index: 1882324 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.5250. Min Act: -0.1700
Data Index: 3846195 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.4625. Min Act: -0.1700
Data Index: 5588262 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.4938. Min Act: -0.1700
Data Index: 4764382 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.4625. Min Act: -0.1700
Data Index: 3548407 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.4625. Min Act: -0.1700
Data Index: 3169373 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.4625. Min Act: -0.1700
Data Index: 5643217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.4625. Min Act: -0.1700
Data Index: 2563284 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.4625. Min Act: -0.1700
Data Index: 2565993 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.4625. Min Act: -0.1700
Data Index: 6858698 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7125. Min Range: -4.7125
Max Act: 4.4625. Min Act: -0.1700
Data Index: 3664527 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19