Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2214 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.6883. Min Act: -0.1700
Data Index: 7632271 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.6883. Min Act: -0.1700
Data Index: 7632272 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.6883. Min Act: -0.1700
Data Index: 8150695 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.6258. Min Act: -0.1700
Data Index: 5993295 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.6258. Min Act: -0.1700
Data Index: 2210391 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.6258. Min Act: -0.1700
Data Index: 43569 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.6258. Min Act: -0.1700
Data Index: 6375226 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5633. Min Act: -0.1700
Data Index: 6064765 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5633. Min Act: -0.1695
Data Index: 3034863 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5633. Min Act: -0.1700
Data Index: 854907 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5633. Min Act: -0.1700
Data Index: 6462601 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5633. Min Act: -0.1700
Data Index: 2415558 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5633. Min Act: -0.1700
Data Index: 2834681 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5633. Min Act: -0.1700
Data Index: 2415339 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5008. Min Act: -0.1700
Data Index: 2999014 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5008. Min Act: -0.1696
Data Index: 2999013 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5008. Min Act: -0.1700
Data Index: 2415559 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5008. Min Act: -0.1700
Data Index: 4236749 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5008. Min Act: -0.1700
Data Index: 4584157 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6883. Min Range: -10.6883
Max Act: 10.5008. Min Act: -0.1700
Data Index: 2358610 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19