Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.7572. Min Act: -0.1700
Data Index: 8077143 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.6322. Min Act: -0.1700
Data Index: 7280530 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.6009. Min Act: -0.1700
Data Index: 4034905 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.5072. Min Act: -0.1700
Data Index: 1634528 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.3197. Min Act: -0.1700
Data Index: 2775123 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.3197. Min Act: -0.1700
Data Index: 4175125 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.2884. Min Act: -0.1700
Data Index: 7119660 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.2884. Min Act: -0.1700
Data Index: 8411545 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.2884. Min Act: -0.1700
Data Index: 4777687 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.2259. Min Act: -0.1700
Data Index: 4941923 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.1947. Min Act: -0.1700
Data Index: 579671 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.1947. Min Act: -0.1700
Data Index: 4534252 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.2259. Min Act: -0.1700
Data Index: 6764055 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.1634. Min Act: -0.1700
Data Index: 2097104 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.1634. Min Act: -0.1700
Data Index: 1047315 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.1634. Min Act: -0.1700
Data Index: 5156704 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.1009. Min Act: -0.1700
Data Index: 5357927 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.1009. Min Act: -0.1700
Data Index: 6253517 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.0697. Min Act: -0.1700
Data Index: 6123209 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7572. Min Range: -6.7572
Max Act: 6.0697. Min Act: -0.1700
Data Index: 6865710 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19