Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6047 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3712. Min Range: -11.3712
Max Act: 11.3712. Min Act: -0.1700
Data Index: 2258830 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.9962. Min Act: -0.1700
Data Index: 351631 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.9962. Min Act: -0.1700
Data Index: 8182925 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.7462. Min Act: -0.1700
Data Index: 4177122 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.7462. Min Act: -0.1700
Data Index: 4975558 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.6212. Min Act: -0.1700
Data Index: 272667 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.6837. Min Act: -0.1700
Data Index: 1443149 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.5587. Min Act: -0.1700
Data Index: 5703413 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.6212. Min Act: -0.1700
Data Index: 7517177 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.5587. Min Act: -0.1700
Data Index: 3149079 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.5587. Min Act: -0.1700
Data Index: 6393483 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.4962. Min Act: -0.1700
Data Index: 589637 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.4962. Min Act: -0.1700
Data Index: 589635 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.4962. Min Act: -0.1700
Data Index: 8051957 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.4962. Min Act: -0.1700
Data Index: 1742303 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.4962. Min Act: -0.1700
Data Index: 6393482 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.4962. Min Act: -0.1700
Data Index: 6820189 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.4962. Min Act: -0.1700
Data Index: 1146426 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.4962. Min Act: -0.1700
Data Index: 6179169 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3712. Min Range: -11.3712
Max Act: 10.4962. Min Act: -0.1700
Data Index: 8095638 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19