Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 199 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7611. Min Act: -0.1696
Data Index: 6827861 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7438. Min Act: -0.1700
Data Index: 3609168 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7352. Min Act: -0.1700
Data Index: 8448812 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7438. Min Act: -0.1699
Data Index: 6308995 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7265. Min Act: -0.1700
Data Index: 2447641 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7179. Min Act: -0.1699
Data Index: 2164999 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7179. Min Act: -0.1700
Data Index: 1588889 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7179. Min Act: -0.1700
Data Index: 5915024 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7092. Min Act: -0.1699
Data Index: 3009737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7179. Min Act: -0.1700
Data Index: 5581327 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7005. Min Act: -0.1700
Data Index: 4909296 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7092. Min Act: -0.1697
Data Index: 4505088 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7092. Min Act: -0.1700
Data Index: 8597597 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7005. Min Act: -0.1700
Data Index: 1033710 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7005. Min Act: -0.1700
Data Index: 3163697 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7005. Min Act: -0.1700
Data Index: 8783152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7092. Min Act: -0.1636
Data Index: 4411984 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.7005. Min Act: -0.1700
Data Index: 3458703 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.6832. Min Act: -0.1697
Data Index: 5915031 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7611. Min Range: -1.7611
Max Act: 1.6919. Min Act: -0.1700
Data Index: 5392949 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19