Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1658 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.7428. Min Act: -0.1700
Data Index: 1210750 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.7428. Min Act: -0.1700
Data Index: 3571437 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.7115. Min Act: -0.1700
Data Index: 1287646 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.7115. Min Act: -0.1700
Data Index: 5551051 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.6802. Min Act: -0.1700
Data Index: 8582186 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.6802. Min Act: -0.1700
Data Index: 6371514 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.6489. Min Act: -0.1700
Data Index: 3175923 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5863. Min Act: -0.1700
Data Index: 6371512 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5863. Min Act: -0.1700
Data Index: 2452898 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.6176. Min Act: -0.1700
Data Index: 1199013 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5863. Min Act: -0.1700
Data Index: 562597 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5550. Min Act: -0.1700
Data Index: 4520172 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5550. Min Act: -0.1700
Data Index: 3678172 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5550. Min Act: -0.1700
Data Index: 469547 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5863. Min Act: -0.1700
Data Index: 155907 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5550. Min Act: -0.1700
Data Index: 3495682 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5237. Min Act: -0.1700
Data Index: 5260602 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5080. Min Act: -0.1700
Data Index: 40347 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5550. Min Act: -0.1700
Data Index: 4964355 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7428. Min Range: -3.7428
Max Act: 3.5237. Min Act: -0.1700
Data Index: 4966162 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19