Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2236 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.5223. Min Act: -0.1700
Data Index: 764571 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.5223. Min Act: -0.1700
Data Index: 5331200 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.3348. Min Act: -0.1700
Data Index: 3627326 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.3973. Min Act: -0.1700
Data Index: 8038794 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.2098. Min Act: -0.1700
Data Index: 1301099 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.2723. Min Act: -0.1700
Data Index: 8485000 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.2098. Min Act: -0.1700
Data Index: 3627327 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.1473. Min Act: -0.1700
Data Index: 1745418 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.0848. Min Act: -0.1700
Data Index: 3155422 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.0223. Min Act: -0.1700
Data Index: 1745401 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5223. Min Range: -9.5223
Max Act: 9.0223. Min Act: -0.1700
Data Index: 5175221 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5223. Min Range: -9.5223
Max Act: 8.9598. Min Act: -0.1700
Data Index: 5306207 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5223. Min Range: -9.5223
Max Act: 8.8973. Min Act: -0.1700
Data Index: 3439594 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5223. Min Range: -9.5223
Max Act: 8.8973. Min Act: -0.1700
Data Index: 823846 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5223. Min Range: -9.5223
Max Act: 8.8348. Min Act: -0.1700
Data Index: 1131995 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5223. Min Range: -9.5223
Max Act: 8.8348. Min Act: -0.1700
Data Index: 4090853 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5223. Min Range: -9.5223
Max Act: 8.7723. Min Act: -0.1700
Data Index: 729994 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5223. Min Range: -9.5223
Max Act: 8.7098. Min Act: -0.1700
Data Index: 6942794 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5223. Min Range: -9.5223
Max Act: 8.7723. Min Act: -0.1700
Data Index: 1849387 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5223. Min Range: -9.5223
Max Act: 8.7723. Min Act: -0.1700
Data Index: 2250013 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19