Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2601. Min Range: -7.2601
Max Act: 7.2601. Min Act: -0.1700
Data Index: 5556174 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2601. Min Range: -7.2601
Max Act: 7.1351. Min Act: -0.1700
Data Index: 1240092 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.7914. Min Act: -0.1700
Data Index: 5550388 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.6664. Min Act: -0.1700
Data Index: 777643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.5414. Min Act: -0.1700
Data Index: 5041224 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.5414. Min Act: -0.1700
Data Index: 1620528 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.5414. Min Act: -0.1700
Data Index: 2383043 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.4789. Min Act: -0.1700
Data Index: 7964352 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.4789. Min Act: -0.1700
Data Index: 6662116 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.4476. Min Act: -0.1700
Data Index: 4269461 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.4476. Min Act: -0.1700
Data Index: 1618938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.4164. Min Act: -0.1700
Data Index: 2019303 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.3851. Min Act: -0.1700
Data Index: 916936 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.3539. Min Act: -0.1700
Data Index: 1189892 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.3539. Min Act: -0.1700
Data Index: 4292988 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.3539. Min Act: -0.1700
Data Index: 3400886 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.3226. Min Act: -0.1700
Data Index: 5931281 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.3226. Min Act: -0.1700
Data Index: 7002703 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.3226. Min Act: -0.1700
Data Index: 4701002 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2601. Min Range: -7.2601
Max Act: 6.3226. Min Act: -0.1700
Data Index: 2067267 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19