Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.6351. Min Act: -0.1700
Data Index: 7701883 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.5101. Min Act: -0.1700
Data Index: 1044443 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.5101. Min Act: -0.1700
Data Index: 8028072 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.5101. Min Act: -0.1700
Data Index: 4453834 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.4476. Min Act: -0.1700
Data Index: 4513066 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.4476. Min Act: -0.1700
Data Index: 3649871 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.4476. Min Act: -0.1700
Data Index: 6699429 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.4164. Min Act: -0.1700
Data Index: 6864319 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.4164. Min Act: -0.1700
Data Index: 1885712 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.3226. Min Act: -0.1700
Data Index: 543490 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.3226. Min Act: -0.1700
Data Index: 7066428 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.2914. Min Act: -0.1700
Data Index: 1299416 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.2914. Min Act: -0.1700
Data Index: 4956815 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.2601. Min Act: -0.1700
Data Index: 2295758 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.2601. Min Act: -0.1700
Data Index: 8409333 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.2601. Min Act: -0.1700
Data Index: 4263390 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.2601. Min Act: -0.1700
Data Index: 2277127 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.2601. Min Act: -0.1700
Data Index: 8141106 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.2289. Min Act: -0.1700
Data Index: 207655 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6351. Min Range: -7.6351
Max Act: 7.2601. Min Act: -0.1700
Data Index: 5369036 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19