Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5048 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.2399. Min Act: -0.1700
Data Index: 6167949 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.1774. Min Act: -0.1700
Data Index: 7876279 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.1774. Min Act: -0.1700
Data Index: 3031519 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.1774. Min Act: -0.1700
Data Index: 7477909 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.1461. Min Act: -0.1700
Data Index: 7091351 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.1149. Min Act: -0.1700
Data Index: 557742 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0836. Min Act: -0.1700
Data Index: 7122665 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0523. Min Act: -0.1700
Data Index: 7629212 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0523. Min Act: -0.1700
Data Index: 1808458 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0523. Min Act: -0.1700
Data Index: 3863123 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0211. Min Act: -0.1700
Data Index: 1194508 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0211. Min Act: -0.1700
Data Index: 7816244 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2399. Min Range: -4.2399
Max Act: 4.0211. Min Act: -0.1700
Data Index: 7484855 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9898. Min Act: -0.1700
Data Index: 6660007 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9898. Min Act: -0.1700
Data Index: 2554356 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9898. Min Act: -0.1700
Data Index: 5050963 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9586. Min Act: -0.1700
Data Index: 1827167 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9586. Min Act: -0.1700
Data Index: 4362037 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9273. Min Act: -0.1700
Data Index: 8239640 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2399. Min Range: -4.2399
Max Act: 3.9273. Min Act: -0.1700
Data Index: 4975021 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19