Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4467 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3941. Min Range: -6.3941
Max Act: 6.3941. Min Act: -0.1700
Data Index: 3329176 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3941. Min Range: -6.3941
Max Act: 6.3316. Min Act: -0.1700
Data Index: 4433565 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3941. Min Range: -6.3941
Max Act: 6.3628. Min Act: -0.1700
Data Index: 6221879 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3941. Min Range: -6.3941
Max Act: 6.1128. Min Act: -0.1700
Data Index: 7074455 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3941. Min Range: -6.3941
Max Act: 6.0503. Min Act: -0.1700
Data Index: 5306353 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.9253. Min Act: -0.1700
Data Index: 748762 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.9253. Min Act: -0.1700
Data Index: 7291039 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.9253. Min Act: -0.1700
Data Index: 2948523 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8941. Min Act: -0.1700
Data Index: 3693132 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8941. Min Act: -0.1700
Data Index: 7775567 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8941. Min Act: -0.1700
Data Index: 3716233 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8628. Min Act: -0.1700
Data Index: 979294 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8941. Min Act: -0.1700
Data Index: 5716693 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8316. Min Act: -0.1700
Data Index: 4981851 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8628. Min Act: -0.1700
Data Index: 4986986 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8628. Min Act: -0.1700
Data Index: 4270064 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8628. Min Act: -0.1700
Data Index: 809323 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8628. Min Act: -0.1700
Data Index: 3908669 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8628. Min Act: -0.1700
Data Index: 7040846 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3941. Min Range: -6.3941
Max Act: 5.8628. Min Act: -0.1700
Data Index: 2510987 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19