Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4070 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.7034. Min Act: -0.1700
Data Index: 7765431 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.4221. Min Act: -0.1700
Data Index: 3195371 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.2971. Min Act: -0.1700
Data Index: 7140786 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.3284. Min Act: -0.1700
Data Index: 4302626 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.3284. Min Act: -0.1700
Data Index: 1205956 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.2659. Min Act: -0.1700
Data Index: 8281466 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.2034. Min Act: -0.1700
Data Index: 8637952 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.2034. Min Act: -0.1700
Data Index: 4585690 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1409. Min Act: -0.1700
Data Index: 602868 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1721. Min Act: -0.1700
Data Index: 2970056 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1721. Min Act: -0.1700
Data Index: 8684217 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1721. Min Act: -0.1700
Data Index: 70530 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1409. Min Act: -0.1700
Data Index: 3799314 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1721. Min Act: -0.1700
Data Index: 2824234 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1096. Min Act: -0.1700
Data Index: 3396856 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1409. Min Act: -0.1700
Data Index: 3412186 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1096. Min Act: -0.1700
Data Index: 3767123 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1096. Min Act: -0.1700
Data Index: 8597455 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.1096. Min Act: -0.1700
Data Index: 8140362 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7034. Min Range: -6.7034
Max Act: 6.0784. Min Act: -0.1700
Data Index: 2705372 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19