Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 632 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.9096. Min Act: -0.1697
Data Index: 4617341 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.8755. Min Act: -0.1700
Data Index: 798498 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.8241. Min Act: -0.1700
Data Index: 3412474 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7724. Min Act: -0.1700
Data Index: 860205 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7897. Min Act: -0.1700
Data Index: 6686421 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7552. Min Act: -0.1630
Data Index: 7166434 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7552. Min Act: -0.1700
Data Index: 7184099 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7724. Min Act: -0.1700
Data Index: 2790643 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7724. Min Act: -0.1700
Data Index: 7003265 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7724. Min Act: -0.1700
Data Index: 5775423 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7552. Min Act: -0.1699
Data Index: 362833 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7379. Min Act: -0.1700
Data Index: 1593335 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7552. Min Act: -0.1700
Data Index: 8501631 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7552. Min Act: -0.1696
Data Index: 6878535 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7206. Min Act: -0.1630
Data Index: 93260 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7379. Min Act: -0.1695
Data Index: 8030180 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7379. Min Act: -0.1700
Data Index: 8629654 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7379. Min Act: -0.1698
Data Index: 4667800 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7379. Min Act: -0.1700
Data Index: 2614678 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9096. Min Range: -1.9096
Max Act: 1.7379. Min Act: -0.1697
Data Index: 4210773 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19