Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2829 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.9824. Min Act: -0.1700
Data Index: 7980561 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.9824. Min Act: -0.1700
Data Index: 7268535 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.8574. Min Act: -0.1700
Data Index: 3643445 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.8574. Min Act: -0.1700
Data Index: 7929579 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.7949. Min Act: -0.1700
Data Index: 5319189 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.7949. Min Act: -0.1700
Data Index: 8627917 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.7949. Min Act: -0.1700
Data Index: 4489089 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.7949. Min Act: -0.1700
Data Index: 626815 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.7324. Min Act: -0.1700
Data Index: 1087480 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.7324. Min Act: -0.1700
Data Index: 7114875 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.7324. Min Act: -0.1700
Data Index: 2795146 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.7324. Min Act: -0.1700
Data Index: 3047511 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.7324. Min Act: -0.1700
Data Index: 3741526 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.6699. Min Act: -0.1700
Data Index: 4034331 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.6699. Min Act: -0.1700
Data Index: 3810666 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.6699. Min Act: -0.1700
Data Index: 2043924 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.6699. Min Act: -0.1700
Data Index: 7517254 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.6699. Min Act: -0.1700
Data Index: 4393427 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.6699. Min Act: -0.1700
Data Index: 6837911 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9824. Min Range: -10.9824
Max Act: 10.6074. Min Act: -0.1700
Data Index: 748923 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19