Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3808 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.9577. Min Act: -0.1700
Data Index: 6224233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.9407. Min Act: -0.1700
Data Index: 6458173 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8726. Min Act: -0.1700
Data Index: 3259176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8726. Min Act: -0.1700
Data Index: 8549060 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8383. Min Act: -0.1700
Data Index: 4819878 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8212. Min Act: -0.1700
Data Index: 1449208 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8212. Min Act: -0.1700
Data Index: 542934 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8212. Min Act: -0.1700
Data Index: 927670 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8212. Min Act: -0.1700
Data Index: 2431462 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8040. Min Act: -0.1700
Data Index: 4187975 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8040. Min Act: -0.1700
Data Index: 1332426 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8040. Min Act: -0.1700
Data Index: 2522109 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.7868. Min Act: -0.1700
Data Index: 5127859 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.7868. Min Act: -0.1700
Data Index: 6786967 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8040. Min Act: -0.1700
Data Index: 3727802 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8040. Min Act: -0.1700
Data Index: 2923351 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8040. Min Act: -0.1700
Data Index: 2971408 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.7868. Min Act: -0.1700
Data Index: 142679 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8040. Min Act: -0.1700
Data Index: 1193063 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9577. Min Range: -1.9577
Max Act: 1.8040. Min Act: -0.1700
Data Index: 1994653 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19