Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5267 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.5809. Min Act: -0.1700
Data Index: 7027114 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.4559. Min Act: -0.1700
Data Index: 6066676 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.4559. Min Act: -0.1700
Data Index: 643474 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.4559. Min Act: -0.1700
Data Index: 7364846 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.4247. Min Act: -0.1700
Data Index: 1592524 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3934. Min Act: -0.1700
Data Index: 7322214 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3934. Min Act: -0.1700
Data Index: 8581246 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3934. Min Act: -0.1700
Data Index: 500464 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3934. Min Act: -0.1700
Data Index: 1271768 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3622. Min Act: -0.1700
Data Index: 7742013 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3622. Min Act: -0.1700
Data Index: 3796337 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2997. Min Act: -0.1700
Data Index: 3390727 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3309. Min Act: -0.1700
Data Index: 7635823 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3309. Min Act: -0.1700
Data Index: 1972469 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2997. Min Act: -0.1700
Data Index: 7742011 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2997. Min Act: -0.1700
Data Index: 8765428 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2684. Min Act: -0.1700
Data Index: 329668 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2684. Min Act: -0.1700
Data Index: 6157100 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2372. Min Act: -0.1700
Data Index: 3588719 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2372. Min Act: -0.1700
Data Index: 3432615 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19