Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3599 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.2414. Min Act: -0.1700
Data Index: 7169523 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.2101. Min Act: -0.1700
Data Index: 7494849 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.1476. Min Act: -0.1700
Data Index: 2898139 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.1163. Min Act: -0.1700
Data Index: 2416318 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.1163. Min Act: -0.1700
Data Index: 70012 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.0851. Min Act: -0.1700
Data Index: 5295936 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.0538. Min Act: -0.1700
Data Index: 1602920 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.0851. Min Act: -0.1700
Data Index: 8675867 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.0538. Min Act: -0.1700
Data Index: 2221009 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.0226. Min Act: -0.1700
Data Index: 8675868 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.0538. Min Act: -0.1700
Data Index: 8462922 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.0226. Min Act: -0.1700
Data Index: 2061277 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2414. Min Range: -4.2414
Max Act: 3.9913. Min Act: -0.1700
Data Index: 4600356 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2414. Min Range: -4.2414
Max Act: 4.0226. Min Act: -0.1700
Data Index: 485483 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2414. Min Range: -4.2414
Max Act: 3.9913. Min Act: -0.1700
Data Index: 5314785 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2414. Min Range: -4.2414
Max Act: 3.9600. Min Act: -0.1700
Data Index: 4809460 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2414. Min Range: -4.2414
Max Act: 3.9600. Min Act: -0.1700
Data Index: 1538040 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2414. Min Range: -4.2414
Max Act: 3.9913. Min Act: -0.1700
Data Index: 3383327 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2414. Min Range: -4.2414
Max Act: 3.9913. Min Act: -0.1700
Data Index: 1999999 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2414. Min Range: -4.2414
Max Act: 3.9288. Min Act: -0.1700
Data Index: 591960 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19