Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.6914. Min Act: -0.1700
Data Index: 4756584 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.6289. Min Act: -0.1700
Data Index: 6051832 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.6289. Min Act: -0.1700
Data Index: 215545 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.5664. Min Act: -0.1700
Data Index: 545615 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.5351. Min Act: -0.1700
Data Index: 3925549 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.4414. Min Act: -0.1700
Data Index: 4838937 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.4414. Min Act: -0.1700
Data Index: 8624081 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.3789. Min Act: -0.1700
Data Index: 5490601 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.3789. Min Act: -0.1700
Data Index: 1543378 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.3164. Min Act: -0.1700
Data Index: 5487847 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.2851. Min Act: -0.1700
Data Index: 3613630 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.2851. Min Act: -0.1700
Data Index: 4062659 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.2851. Min Act: -0.1700
Data Index: 7922544 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.2851. Min Act: -0.1700
Data Index: 3241043 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.2539. Min Act: -0.1700
Data Index: 2286708 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.2226. Min Act: -0.1700
Data Index: 7897290 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.2539. Min Act: -0.1700
Data Index: 604514 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.2226. Min Act: -0.1700
Data Index: 8212036 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.2226. Min Act: -0.1700
Data Index: 2124080 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6914. Min Range: -5.6914
Max Act: 5.1914. Min Act: -0.1700
Data Index: 5536010 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19