Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.9924. Min Act: -0.1700
Data Index: 5048089 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.9133. Min Act: -0.1700
Data Index: 1880774 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8974. Min Act: -0.1700
Data Index: 340912 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8815. Min Act: -0.1700
Data Index: 4898761 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8339. Min Act: -0.1700
Data Index: 6224437 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8180. Min Act: -0.1700
Data Index: 6412349 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8021. Min Act: -0.1700
Data Index: 8215656 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8180. Min Act: -0.1700
Data Index: 5318813 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8339. Min Act: -0.1700
Data Index: 4260102 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8180. Min Act: -0.1700
Data Index: 2212553 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8339. Min Act: -0.1700
Data Index: 428777 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8021. Min Act: -0.1700
Data Index: 4023261 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8021. Min Act: -0.1700
Data Index: 2374694 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8021. Min Act: -0.1700
Data Index: 4803412 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.7542. Min Act: -0.1700
Data Index: 2426545 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8021. Min Act: -0.1700
Data Index: 190557 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.8021. Min Act: -0.1700
Data Index: 4935634 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.7702. Min Act: -0.1700
Data Index: 4947916 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.7542. Min Act: -0.1700
Data Index: 1429949 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9924. Min Range: -2.9924
Max Act: 2.7383. Min Act: -0.1700
Data Index: 3133538 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19