Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3131 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0253. Min Range: -6.0253
Max Act: 6.0253. Min Act: -0.1700
Data Index: 3202626 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.9941. Min Act: -0.1700
Data Index: 8030234 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.9628. Min Act: -0.1700
Data Index: 7772281 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.9628. Min Act: -0.1700
Data Index: 4319074 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.9003. Min Act: -0.1700
Data Index: 3046381 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8691. Min Act: -0.1700
Data Index: 7962576 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8691. Min Act: -0.1700
Data Index: 5530182 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8378. Min Act: -0.1700
Data Index: 3530305 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8378. Min Act: -0.1700
Data Index: 6514423 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8066. Min Act: -0.1700
Data Index: 3224097 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8066. Min Act: -0.1700
Data Index: 2090592 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8066. Min Act: -0.1700
Data Index: 158141 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.8066. Min Act: -0.1700
Data Index: 2599097 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.6816. Min Act: -0.1700
Data Index: 3968076 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.7128. Min Act: -0.1700
Data Index: 4240033 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.7128. Min Act: -0.1700
Data Index: 8390836 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.6816. Min Act: -0.1700
Data Index: 8116371 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.6816. Min Act: -0.1700
Data Index: 3505670 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.6816. Min Act: -0.1700
Data Index: 818432 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0253. Min Range: -6.0253
Max Act: 5.5878. Min Act: -0.1700
Data Index: 7750367 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19