Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.9175. Min Act: -0.1700
Data Index: 19441 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.8550. Min Act: -0.1700
Data Index: 4545615 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.5425. Min Act: -0.1700
Data Index: 1898338 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.4487. Min Act: -0.1700
Data Index: 6553479 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.4487. Min Act: -0.1700
Data Index: 1534930 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.4487. Min Act: -0.1700
Data Index: 1398648 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.4487. Min Act: -0.1700
Data Index: 6035134 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.4487. Min Act: -0.1700
Data Index: 3737057 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.4175. Min Act: -0.1700
Data Index: 6605147 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.3862. Min Act: -0.1700
Data Index: 8223181 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.3862. Min Act: -0.1700
Data Index: 4565187 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.3550. Min Act: -0.1700
Data Index: 4298863 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.3237. Min Act: -0.1700
Data Index: 7489620 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.2612. Min Act: -0.1700
Data Index: 3443398 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.2925. Min Act: -0.1700
Data Index: 8545402 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.2925. Min Act: -0.1700
Data Index: 1490647 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.2612. Min Act: -0.1700
Data Index: 4328363 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.2612. Min Act: -0.1700
Data Index: 6100569 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.2300. Min Act: -0.1700
Data Index: 813066 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9175. Min Range: -6.9175
Max Act: 6.2300. Min Act: -0.1700
Data Index: 7615977 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19