Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.5963. Min Act: -0.1700
Data Index: 3539901 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.6275. Min Act: -0.1700
Data Index: 6632815 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.4400. Min Act: -0.1700
Data Index: 8670467 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.4088. Min Act: -0.1700
Data Index: 1172213 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.3463. Min Act: -0.1700
Data Index: 3538412 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.3150. Min Act: -0.1700
Data Index: 7651438 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.2838. Min Act: -0.1700
Data Index: 410347 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1900. Min Act: -0.1700
Data Index: 2481663 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1900. Min Act: -0.1700
Data Index: 4140856 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1588. Min Act: -0.1700
Data Index: 4653904 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1275. Min Act: -0.1700
Data Index: 3082991 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1275. Min Act: -0.1700
Data Index: 4731566 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1275. Min Act: -0.1700
Data Index: 3951217 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.0650. Min Act: -0.1700
Data Index: 2453587 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.0963. Min Act: -0.1700
Data Index: 8732780 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.0650. Min Act: -0.1700
Data Index: 4027936 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.0338. Min Act: -0.1700
Data Index: 6625128 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.0338. Min Act: -0.1700
Data Index: 2445787 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.0338. Min Act: -0.1700
Data Index: 1951521 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.0650. Min Act: -0.1700
Data Index: 8338495 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19