Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.5394. Min Act: -0.1700
Data Index: 2691403 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.4747. Min Act: -0.1700
Data Index: 976716 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.4096. Min Act: -0.1700
Data Index: 4680070 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.4096. Min Act: -0.1700
Data Index: 4615759 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.4096. Min Act: -0.1700
Data Index: 804328 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3606. Min Act: -0.1700
Data Index: 4115077 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3606. Min Act: -0.1700
Data Index: 2531321 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3606. Min Act: -0.1700
Data Index: 1366547 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3442. Min Act: -0.1700
Data Index: 3924230 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3442. Min Act: -0.1700
Data Index: 1521514 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3442. Min Act: -0.1700
Data Index: 292724 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3442. Min Act: -0.1700
Data Index: 3895450 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3114. Min Act: -0.1700
Data Index: 6623207 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3114. Min Act: -0.1700
Data Index: 6731974 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3114. Min Act: -0.1700
Data Index: 4851432 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3114. Min Act: -0.1700
Data Index: 2939138 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3114. Min Act: -0.1700
Data Index: 7895571 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3114. Min Act: -0.1700
Data Index: 7070015 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3114. Min Act: -0.1700
Data Index: 4321819 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5394. Min Range: -2.5394
Max Act: 2.3114. Min Act: -0.1700
Data Index: 8487810 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19