Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.2499. Min Act: -0.1700
Data Index: 1046419 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.2499. Min Act: -0.1700
Data Index: 5091425 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.2342. Min Act: -0.1700
Data Index: 3276324 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.2499. Min Act: -0.1700
Data Index: 8294362 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.1870. Min Act: -0.1700
Data Index: 5396780 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.1555. Min Act: -0.1700
Data Index: 1895280 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.1555. Min Act: -0.1700
Data Index: 5406393 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.1240. Min Act: -0.1700
Data Index: 2705044 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.1398. Min Act: -0.1700
Data Index: 2427191 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.1240. Min Act: -0.1700
Data Index: 7745827 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.1240. Min Act: -0.1700
Data Index: 7527692 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.1083. Min Act: -0.1700
Data Index: 7183463 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.0925. Min Act: -0.1700
Data Index: 5085144 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.0925. Min Act: -0.1700
Data Index: 6574438 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.0767. Min Act: -0.1700
Data Index: 5474516 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.0767. Min Act: -0.1700
Data Index: 6229497 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.0767. Min Act: -0.1700
Data Index: 414013 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.0767. Min Act: -0.1700
Data Index: 282453 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.0767. Min Act: -0.1700
Data Index: 8611038 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2499. Min Range: -3.2499
Max Act: 3.0610. Min Act: -0.1700
Data Index: 7774669 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19