Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.1611. Min Range: -10.1611
Max Act: 10.1611. Min Act: -0.1700
Data Index: 2264937 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.8486. Min Act: -0.1700
Data Index: 6207948 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.8486. Min Act: -0.1700
Data Index: 7218948 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.7236. Min Act: -0.1700
Data Index: 6207937 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.7861. Min Act: -0.1700
Data Index: 1134013 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.6611. Min Act: -0.1700
Data Index: 373458 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.7236. Min Act: -0.1700
Data Index: 5219344 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.5986. Min Act: -0.1700
Data Index: 6493516 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.4736. Min Act: -0.1700
Data Index: 2731400 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.4111. Min Act: -0.1700
Data Index: 533882 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.4111. Min Act: -0.1700
Data Index: 5798149 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.4111. Min Act: -0.1700
Data Index: 5158122 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.3486. Min Act: -0.1697
Data Index: 6704931 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.3486. Min Act: -0.1700
Data Index: 8078995 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.3486. Min Act: -0.1700
Data Index: 5443590 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.3486. Min Act: -0.1700
Data Index: 6757297 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.3486. Min Act: -0.1700
Data Index: 4256586 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.3486. Min Act: -0.1700
Data Index: 373472 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.3486. Min Act: -0.1698
Data Index: 5714395 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1611. Min Range: -10.1611
Max Act: 9.2861. Min Act: -0.1699
Data Index: 5633667 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19