Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1274. Min Range: -6.1274
Max Act: 6.1274. Min Act: -0.1699
Data Index: 6631486 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1274. Min Range: -6.1274
Max Act: 6.0961. Min Act: -0.1700
Data Index: 6631485 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1274. Min Range: -6.1274
Max Act: 6.0024. Min Act: -0.1696
Data Index: 7824835 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.9399. Min Act: -0.1700
Data Index: 5505594 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.9399. Min Act: -0.1700
Data Index: 3639752 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.8774. Min Act: -0.1700
Data Index: 1464648 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.8461. Min Act: -0.1700
Data Index: 5505590 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.8461. Min Act: -0.1700
Data Index: 5505597 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.7836. Min Act: -0.1700
Data Index: 471993 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.7524. Min Act: -0.1700
Data Index: 251826 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.7836. Min Act: -0.1700
Data Index: 5505596 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.7211. Min Act: -0.1700
Data Index: 3297915 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.7211. Min Act: -0.1700
Data Index: 2738804 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.6899. Min Act: -0.1700
Data Index: 2957630 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.6274. Min Act: -0.1700
Data Index: 6956621 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.5961. Min Act: -0.1700
Data Index: 2455048 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.6274. Min Act: -0.1700
Data Index: 2407010 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.6274. Min Act: -0.1700
Data Index: 3000711 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.6274. Min Act: -0.1700
Data Index: 7280510 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1274. Min Range: -6.1274
Max Act: 5.6274. Min Act: -0.1700
Data Index: 4944310 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19