Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2451 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.9165. Min Act: -0.1700
Data Index: 1548119 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.9165. Min Act: -0.1700
Data Index: 4103743 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.8540. Min Act: -0.1700
Data Index: 7771447 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.8228. Min Act: -0.1700
Data Index: 5890591 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.8228. Min Act: -0.1700
Data Index: 3653787 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7915. Min Act: -0.1700
Data Index: 4361394 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7603. Min Act: -0.1700
Data Index: 2684825 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7915. Min Act: -0.1700
Data Index: 990315 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7603. Min Act: -0.1700
Data Index: 2840300 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7603. Min Act: -0.1700
Data Index: 3463761 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7603. Min Act: -0.1700
Data Index: 6016821 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7603. Min Act: -0.1700
Data Index: 8413609 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7603. Min Act: -0.1700
Data Index: 4200154 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7290. Min Act: -0.1700
Data Index: 8169693 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7603. Min Act: -0.1700
Data Index: 6404086 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7290. Min Act: -0.1700
Data Index: 3609623 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.6978. Min Act: -0.1700
Data Index: 3655061 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7290. Min Act: -0.1700
Data Index: 3231648 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.7290. Min Act: -0.1700
Data Index: 6498938 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9165. Min Range: -4.9165
Max Act: 4.6978. Min Act: -0.1700
Data Index: 6594358 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19