Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1605 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.9961. Min Act: -0.1700
Data Index: 4696283 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.9645. Min Act: -0.1700
Data Index: 5147877 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.9645. Min Act: -0.1700
Data Index: 3359050 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.9486. Min Act: -0.1700
Data Index: 5176466 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.9011. Min Act: -0.1700
Data Index: 2863049 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.8852. Min Act: -0.1700
Data Index: 6186845 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.8852. Min Act: -0.1700
Data Index: 776948 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.8694. Min Act: -0.1700
Data Index: 4696282 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.8535. Min Act: -0.1700
Data Index: 4760918 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.8217. Min Act: -0.1700
Data Index: 3943906 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.8535. Min Act: -0.1700
Data Index: 25020 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.8376. Min Act: -0.1700
Data Index: 3728761 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.8376. Min Act: -0.1700
Data Index: 719852 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.8376. Min Act: -0.1700
Data Index: 5307625 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.8058. Min Act: -0.1700
Data Index: 1605156 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.7580. Min Act: -0.1700
Data Index: 5875496 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.7420. Min Act: -0.1700
Data Index: 2778823 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.7260. Min Act: -0.1700
Data Index: 2783081 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.7420. Min Act: -0.1700
Data Index: 5134208 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9961. Min Range: -2.9961
Max Act: 2.7260. Min Act: -0.1700
Data Index: 2005982 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19