Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.4677. Min Act: -0.1700
Data Index: 3676689 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.4052. Min Act: -0.1700
Data Index: 2149338 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.4052. Min Act: -0.1700
Data Index: 4285379 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.3740. Min Act: -0.1700
Data Index: 2417988 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.3427. Min Act: -0.1700
Data Index: 394882 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.3427. Min Act: -0.1700
Data Index: 8540850 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.3115. Min Act: -0.1700
Data Index: 2883854 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.3115. Min Act: -0.1700
Data Index: 1907604 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.2802. Min Act: -0.1700
Data Index: 6006395 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.2802. Min Act: -0.1700
Data Index: 636816 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.2177. Min Act: -0.1700
Data Index: 1650588 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.2177. Min Act: -0.1700
Data Index: 4107251 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.2490. Min Act: -0.1700
Data Index: 4921272 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.1552. Min Act: -0.1700
Data Index: 1840119 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.1865. Min Act: -0.1700
Data Index: 6983573 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.1239. Min Act: -0.1700
Data Index: 6820072 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.1552. Min Act: -0.1700
Data Index: 3135439 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.1865. Min Act: -0.1700
Data Index: 7500695 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.1552. Min Act: -0.1700
Data Index: 7769287 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4677. Min Range: -4.4677
Max Act: 4.1552. Min Act: -0.1700
Data Index: 3769978 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19