Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2228 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0066. Min Range: -8.0066
Max Act: 8.0066. Min Act: -0.1700
Data Index: 6417075 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.6316. Min Act: -0.1699
Data Index: 4168100 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.5066. Min Act: -0.1700
Data Index: 3467520 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.3816. Min Act: -0.1700
Data Index: 5870826 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.3816. Min Act: -0.1700
Data Index: 8557482 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.2566. Min Act: -0.1700
Data Index: 1365445 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.2566. Min Act: -0.1700
Data Index: 5575967 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.1628. Min Act: -0.1700
Data Index: 8256582 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.1941. Min Act: -0.1700
Data Index: 99377 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.1941. Min Act: -0.1700
Data Index: 7097692 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.1941. Min Act: -0.1700
Data Index: 3789382 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.1316. Min Act: -0.1700
Data Index: 2010027 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.1316. Min Act: -0.1700
Data Index: 7254641 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.1003. Min Act: -0.1700
Data Index: 2761385 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.0691. Min Act: -0.1700
Data Index: 2055332 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.1003. Min Act: -0.1700
Data Index: 2316834 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.1003. Min Act: -0.1700
Data Index: 2080598 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.0691. Min Act: -0.1700
Data Index: 5699384 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.0691. Min Act: -0.1700
Data Index: 4169188 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0066. Min Range: -8.0066
Max Act: 7.0691. Min Act: -0.1700
Data Index: 3904074 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19