Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4176 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.9809. Min Act: -0.1700
Data Index: 734228 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.9497. Min Act: -0.1700
Data Index: 1950289 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.9184. Min Act: -0.1700
Data Index: 4608722 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.8559. Min Act: -0.1700
Data Index: 6543167 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.8247. Min Act: -0.1700
Data Index: 6132465 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.7934. Min Act: -0.1700
Data Index: 5296939 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.7622. Min Act: -0.1700
Data Index: 6334695 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.6684. Min Act: -0.1700
Data Index: 7871281 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.6684. Min Act: -0.1700
Data Index: 6178372 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.6997. Min Act: -0.1700
Data Index: 86502 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.6372. Min Act: -0.1700
Data Index: 2501272 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.6372. Min Act: -0.1700
Data Index: 2885902 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.6059. Min Act: -0.1700
Data Index: 3618475 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.5747. Min Act: -0.1700
Data Index: 2716323 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.5434. Min Act: -0.1700
Data Index: 7269699 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.5747. Min Act: -0.1700
Data Index: 2077246 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.5747. Min Act: -0.1700
Data Index: 3601362 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.5747. Min Act: -0.1700
Data Index: 1373110 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.5747. Min Act: -0.1700
Data Index: 7329845 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9809. Min Range: -5.9809
Max Act: 5.5122. Min Act: -0.1700
Data Index: 7512486 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19