Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.7823. Min Act: -0.1700
Data Index: 3302161 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.7823. Min Act: -0.1700
Data Index: 1468879 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.7511. Min Act: -0.1700
Data Index: 5985470 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.7198. Min Act: -0.1700
Data Index: 1190322 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.7511. Min Act: -0.1700
Data Index: 8542317 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.6886. Min Act: -0.1700
Data Index: 8632364 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.7198. Min Act: -0.1700
Data Index: 105493 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.6573. Min Act: -0.1700
Data Index: 103446 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.6573. Min Act: -0.1700
Data Index: 1002546 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.6886. Min Act: -0.1700
Data Index: 5934633 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.6261. Min Act: -0.1700
Data Index: 2952762 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.5948. Min Act: -0.1700
Data Index: 262029 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.5948. Min Act: -0.1700
Data Index: 6073062 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.6261. Min Act: -0.1700
Data Index: 2796475 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.5948. Min Act: -0.1700
Data Index: 4280037 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.5948. Min Act: -0.1700
Data Index: 3941928 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.5948. Min Act: -0.1700
Data Index: 6946122 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.5636. Min Act: -0.1700
Data Index: 1415094 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.5636. Min Act: -0.1700
Data Index: 971564 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7823. Min Range: -5.7823
Max Act: 5.5948. Min Act: -0.1700
Data Index: 1999069 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19