Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0872. Min Range: -6.0872
Max Act: 6.0872. Min Act: -0.1700
Data Index: 2426947 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.8684. Min Act: -0.1700
Data Index: 411381 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.8372. Min Act: -0.1700
Data Index: 344697 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.8684. Min Act: -0.1700
Data Index: 6214640 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.8372. Min Act: -0.1700
Data Index: 7442724 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.8059. Min Act: -0.1700
Data Index: 4511709 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.7747. Min Act: -0.1700
Data Index: 1691606 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.7434. Min Act: -0.1700
Data Index: 6732457 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.7434. Min Act: -0.1700
Data Index: 4717014 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.7747. Min Act: -0.1700
Data Index: 2630366 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.6809. Min Act: -0.1700
Data Index: 994075 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.7122. Min Act: -0.1700
Data Index: 1713469 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.7122. Min Act: -0.1700
Data Index: 4639734 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.7122. Min Act: -0.1700
Data Index: 7762176 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.7434. Min Act: -0.1700
Data Index: 4514016 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.7122. Min Act: -0.1700
Data Index: 2737879 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.7122. Min Act: -0.1700
Data Index: 2507867 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.6809. Min Act: -0.1700
Data Index: 7320220 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.6809. Min Act: -0.1700
Data Index: 6878885 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0872. Min Range: -6.0872
Max Act: 5.6497. Min Act: -0.1700
Data Index: 3198258 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19