Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3834 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.8191. Min Act: -0.1700
Data Index: 3500344 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.8191. Min Act: -0.1700
Data Index: 594758 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.7878. Min Act: -0.1700
Data Index: 7052828 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.7566. Min Act: -0.1700
Data Index: 2101723 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.7566. Min Act: -0.1700
Data Index: 638652 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.7566. Min Act: -0.1700
Data Index: 7175087 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.7253. Min Act: -0.1700
Data Index: 1548321 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.7253. Min Act: -0.1700
Data Index: 7509459 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.7566. Min Act: -0.1700
Data Index: 5545733 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6628. Min Act: -0.1700
Data Index: 7121070 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6628. Min Act: -0.1700
Data Index: 6689734 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6628. Min Act: -0.1700
Data Index: 8751564 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6628. Min Act: -0.1700
Data Index: 5083051 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6316. Min Act: -0.1700
Data Index: 3363521 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6316. Min Act: -0.1700
Data Index: 3977866 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6316. Min Act: -0.1700
Data Index: 6813555 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6316. Min Act: -0.1700
Data Index: 7838794 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6003. Min Act: -0.1700
Data Index: 5857793 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6003. Min Act: -0.1700
Data Index: 7394766 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8191. Min Range: -5.8191
Max Act: 5.6003. Min Act: -0.1700
Data Index: 2003773 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19