Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4993 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6628. Min Range: -6.6628
Max Act: 6.6628. Min Act: -0.1700
Data Index: 1707880 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6628. Min Range: -6.6628
Max Act: 6.2878. Min Act: -0.1700
Data Index: 1254725 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6628. Min Range: -6.6628
Max Act: 6.1940. Min Act: -0.1700
Data Index: 3467207 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6628. Min Range: -6.6628
Max Act: 6.1940. Min Act: -0.1700
Data Index: 2807184 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6628. Min Range: -6.6628
Max Act: 6.1628. Min Act: -0.1700
Data Index: 5067377 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6628. Min Range: -6.6628
Max Act: 6.1315. Min Act: -0.1700
Data Index: 8429225 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6628. Min Range: -6.6628
Max Act: 6.0690. Min Act: -0.1700
Data Index: 196763 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6628. Min Range: -6.6628
Max Act: 6.0690. Min Act: -0.1700
Data Index: 7940190 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6628. Min Range: -6.6628
Max Act: 6.0378. Min Act: -0.1700
Data Index: 2595870 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6628. Min Range: -6.6628
Max Act: 6.0065. Min Act: -0.1700
Data Index: 3336996 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6628. Min Range: -6.6628
Max Act: 5.9753. Min Act: -0.1700
Data Index: 4727991 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6628. Min Range: -6.6628
Max Act: 5.9753. Min Act: -0.1700
Data Index: 8326479 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6628. Min Range: -6.6628
Max Act: 5.9753. Min Act: -0.1700
Data Index: 4528314 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6628. Min Range: -6.6628
Max Act: 5.9440. Min Act: -0.1700
Data Index: 6194931 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6628. Min Range: -6.6628
Max Act: 5.9128. Min Act: -0.1700
Data Index: 3464842 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6628. Min Range: -6.6628
Max Act: 5.9128. Min Act: -0.1700
Data Index: 5654663 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6628. Min Range: -6.6628
Max Act: 5.9128. Min Act: -0.1700
Data Index: 3348668 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6628. Min Range: -6.6628
Max Act: 5.9128. Min Act: -0.1700
Data Index: 7421446 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6628. Min Range: -6.6628
Max Act: 5.8815. Min Act: -0.1700
Data Index: 4620254 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6628. Min Range: -6.6628
Max Act: 5.8815. Min Act: -0.1700
Data Index: 5796781 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19