Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.4073. Min Act: -0.1700
Data Index: 8590701 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.2198. Min Act: -0.1700
Data Index: 6676312 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.1260. Min Act: -0.1700
Data Index: 8717649 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.0948. Min Act: -0.1700
Data Index: 6025390 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.0635. Min Act: -0.1700
Data Index: 4321314 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.0323. Min Act: -0.1700
Data Index: 3675567 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.0010. Min Act: -0.1700
Data Index: 1544407 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.0010. Min Act: -0.1700
Data Index: 1986621 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.0323. Min Act: -0.1700
Data Index: 5382666 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.0323. Min Act: -0.1700
Data Index: 8717643 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.0323. Min Act: -0.1700
Data Index: 8717645 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.0010. Min Act: -0.1700
Data Index: 8662703 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4073. Min Range: -6.4073
Max Act: 6.0010. Min Act: -0.1700
Data Index: 3047325 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4073. Min Range: -6.4073
Max Act: 5.9698. Min Act: -0.1700
Data Index: 2861010 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4073. Min Range: -6.4073
Max Act: 5.9698. Min Act: -0.1700
Data Index: 4345930 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4073. Min Range: -6.4073
Max Act: 5.9385. Min Act: -0.1700
Data Index: 5773929 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4073. Min Range: -6.4073
Max Act: 5.9385. Min Act: -0.1700
Data Index: 2860999 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4073. Min Range: -6.4073
Max Act: 5.9385. Min Act: -0.1700
Data Index: 3792484 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4073. Min Range: -6.4073
Max Act: 5.8760. Min Act: -0.1700
Data Index: 426522 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4073. Min Range: -6.4073
Max Act: 5.9073. Min Act: -0.1700
Data Index: 4500338 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19