Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.6461. Min Act: -0.1700
Data Index: 6244670 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.5836. Min Act: -0.1700
Data Index: 347366 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.4274. Min Act: -0.1700
Data Index: 1440231 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.3336. Min Act: -0.1700
Data Index: 2073259 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.3024. Min Act: -0.1700
Data Index: 986711 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.2711. Min Act: -0.1700
Data Index: 1996914 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.2711. Min Act: -0.1700
Data Index: 5869661 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.2399. Min Act: -0.1700
Data Index: 6236212 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.1774. Min Act: -0.1700
Data Index: 4441826 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.1774. Min Act: -0.1700
Data Index: 6291057 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.1774. Min Act: -0.1700
Data Index: 931762 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.1774. Min Act: -0.1700
Data Index: 3466100 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.1774. Min Act: -0.1700
Data Index: 8209179 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.1774. Min Act: -0.1700
Data Index: 8504871 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.1149. Min Act: -0.1700
Data Index: 3022799 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.1149. Min Act: -0.1700
Data Index: 3120833 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.1149. Min Act: -0.1700
Data Index: 5547809 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.0836. Min Act: -0.1700
Data Index: 67116 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.0836. Min Act: -0.1700
Data Index: 546866 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6461. Min Range: -6.6461
Max Act: 6.0524. Min Act: -0.1700
Data Index: 4631924 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19