Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.7226. Min Act: -0.1700
Data Index: 21151 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.6914. Min Act: -0.1700
Data Index: 277720 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.6289. Min Act: -0.1700
Data Index: 143039 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.5664. Min Act: -0.1700
Data Index: 1957043 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.5351. Min Act: -0.1700
Data Index: 3100066 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.5039. Min Act: -0.1700
Data Index: 2015836 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4726. Min Act: -0.1700
Data Index: 7981948 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4726. Min Act: -0.1700
Data Index: 7917150 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4414. Min Act: -0.1700
Data Index: 2454955 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4414. Min Act: -0.1700
Data Index: 1478622 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4414. Min Act: -0.1700
Data Index: 7314262 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4414. Min Act: -0.1700
Data Index: 3138386 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4414. Min Act: -0.1700
Data Index: 6141556 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4726. Min Act: -0.1700
Data Index: 8503787 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4414. Min Act: -0.1700
Data Index: 351851 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4101. Min Act: -0.1700
Data Index: 6359993 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.4101. Min Act: -0.1700
Data Index: 3453597 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.3789. Min Act: -0.1700
Data Index: 5370529 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.3789. Min Act: -0.1700
Data Index: 7345106 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7226. Min Range: -4.7226
Max Act: 4.3789. Min Act: -0.1700
Data Index: 7511589 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19