Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.9422. Min Act: -0.1700
Data Index: 5427984 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.9422. Min Act: -0.1700
Data Index: 7976617 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.8484. Min Act: -0.1700
Data Index: 4630761 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.8484. Min Act: -0.1700
Data Index: 5321439 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.8484. Min Act: -0.1700
Data Index: 7858971 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.8172. Min Act: -0.1700
Data Index: 4167195 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.8172. Min Act: -0.1700
Data Index: 4012915 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.7547. Min Act: -0.1700
Data Index: 7858976 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.7859. Min Act: -0.1700
Data Index: 3109176 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.7234. Min Act: -0.1700
Data Index: 5060708 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.7234. Min Act: -0.1700
Data Index: 1115324 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6922. Min Act: -0.1700
Data Index: 1115309 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6922. Min Act: -0.1700
Data Index: 6549997 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6609. Min Act: -0.1700
Data Index: 318264 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6922. Min Act: -0.1700
Data Index: 7858972 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6297. Min Act: -0.1700
Data Index: 4012900 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.5984. Min Act: -0.1700
Data Index: 5479346 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.5672. Min Act: -0.1700
Data Index: 3451874 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.5672. Min Act: -0.1700
Data Index: 6595942 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.5672. Min Act: -0.1700
Data Index: 6595941 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19