Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.9746. Min Act: -0.1700
Data Index: 4283451 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.9433. Min Act: -0.1700
Data Index: 2484254 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.8808. Min Act: -0.1700
Data Index: 2385027 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.8496. Min Act: -0.1700
Data Index: 193039 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.8496. Min Act: -0.1700
Data Index: 8103613 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.8496. Min Act: -0.1700
Data Index: 6074542 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.7871. Min Act: -0.1700
Data Index: 5568216 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.8183. Min Act: -0.1700
Data Index: 5747187 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.7558. Min Act: -0.1700
Data Index: 3880708 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.6933. Min Act: -0.1700
Data Index: 4165543 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.6933. Min Act: -0.1700
Data Index: 7920519 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.6621. Min Act: -0.1700
Data Index: 7241522 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.6308. Min Act: -0.1700
Data Index: 4226376 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.6308. Min Act: -0.1700
Data Index: 1250089 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.5996. Min Act: -0.1700
Data Index: 1185689 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.6308. Min Act: -0.1700
Data Index: 7587568 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.5996. Min Act: -0.1700
Data Index: 7415138 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.6308. Min Act: -0.1700
Data Index: 2499081 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.5996. Min Act: -0.1700
Data Index: 6800083 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9746. Min Range: -6.9746
Max Act: 6.5683. Min Act: -0.1700
Data Index: 2795986 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19