Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4925 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.5369. Min Act: -0.1700
Data Index: 463712 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.4744. Min Act: -0.1700
Data Index: 3888250 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.4744. Min Act: -0.1700
Data Index: 4703852 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.3494. Min Act: -0.1700
Data Index: 1699195 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.3494. Min Act: -0.1700
Data Index: 1903173 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.2869. Min Act: -0.1700
Data Index: 3122637 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.1619. Min Act: -0.1700
Data Index: 6204332 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.0994. Min Act: -0.1700
Data Index: 2223454 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.0369. Min Act: -0.1700
Data Index: 2223459 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.0369. Min Act: -0.1700
Data Index: 3782534 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.0369. Min Act: -0.1700
Data Index: 2996490 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5369. Min Range: -12.5369
Max Act: 12.0369. Min Act: -0.1700
Data Index: 8801470 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5369. Min Range: -12.5369
Max Act: 11.9744. Min Act: -0.1700
Data Index: 1800471 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5369. Min Range: -12.5369
Max Act: 11.9119. Min Act: -0.1700
Data Index: 5947975 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5369. Min Range: -12.5369
Max Act: 11.8494. Min Act: -0.1700
Data Index: 5572538 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5369. Min Range: -12.5369
Max Act: 11.9119. Min Act: -0.1700
Data Index: 4296388 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5369. Min Range: -12.5369
Max Act: 11.8494. Min Act: -0.1700
Data Index: 6883310 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5369. Min Range: -12.5369
Max Act: 11.8494. Min Act: -0.1700
Data Index: 6548094 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5369. Min Range: -12.5369
Max Act: 11.8494. Min Act: -0.1700
Data Index: 7521712 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5369. Min Range: -12.5369
Max Act: 11.7869. Min Act: -0.1700
Data Index: 2953632 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19