Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.4496. Min Act: -0.1700
Data Index: 7345530 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.4184. Min Act: -0.1700
Data Index: 2356574 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.3871. Min Act: -0.1700
Data Index: 8543970 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.2621. Min Act: -0.1700
Data Index: 1887465 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.1996. Min Act: -0.1700
Data Index: 5543758 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.1996. Min Act: -0.1700
Data Index: 5169044 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.1371. Min Act: -0.1700
Data Index: 5488660 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.0434. Min Act: -0.1700
Data Index: 2187665 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.0121. Min Act: -0.1700
Data Index: 1964430 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.0121. Min Act: -0.1700
Data Index: 1860518 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4496. Min Range: -6.4496
Max Act: 6.0121. Min Act: -0.1700
Data Index: 5918432 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4496. Min Range: -6.4496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 4145980 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4496. Min Range: -6.4496
Max Act: 5.9809. Min Act: -0.1700
Data Index: 5095979 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4496. Min Range: -6.4496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 3278231 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4496. Min Range: -6.4496
Max Act: 5.9184. Min Act: -0.1700
Data Index: 3189803 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4496. Min Range: -6.4496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 7207160 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4496. Min Range: -6.4496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 2357367 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4496. Min Range: -6.4496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 1750853 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4496. Min Range: -6.4496
Max Act: 5.9184. Min Act: -0.1700
Data Index: 2324645 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4496. Min Range: -6.4496
Max Act: 5.8871. Min Act: -0.1700
Data Index: 8269995 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19