Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.8285. Min Act: -0.1700
Data Index: 1068884 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.5785. Min Act: -0.1700
Data Index: 5034705 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.4847. Min Act: -0.1700
Data Index: 6547749 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.4847. Min Act: -0.1700
Data Index: 8478148 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.4222. Min Act: -0.1700
Data Index: 4631738 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.4222. Min Act: -0.1700
Data Index: 3695304 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3910. Min Act: -0.1700
Data Index: 8491080 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3910. Min Act: -0.1700
Data Index: 8805543 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3910. Min Act: -0.1700
Data Index: 8677560 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3284. Min Act: -0.1700
Data Index: 8104805 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3597. Min Act: -0.1700
Data Index: 3461792 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3597. Min Act: -0.1700
Data Index: 3185786 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3597. Min Act: -0.1700
Data Index: 5592505 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3597. Min Act: -0.1700
Data Index: 780836 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3597. Min Act: -0.1700
Data Index: 3956610 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3597. Min Act: -0.1700
Data Index: 7573546 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3597. Min Act: -0.1700
Data Index: 4964473 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3597. Min Act: -0.1700
Data Index: 1174151 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3284. Min Act: -0.1700
Data Index: 4737476 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8285. Min Range: -4.8285
Max Act: 4.3597. Min Act: -0.1700
Data Index: 4391425 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19