Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3865 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0606. Min Range: -7.0606
Max Act: 7.0606. Min Act: -0.1700
Data Index: 6864735 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.9668. Min Act: -0.1700
Data Index: 4834986 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.8106. Min Act: -0.1700
Data Index: 178985 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.8106. Min Act: -0.1700
Data Index: 4557048 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.8418. Min Act: -0.1700
Data Index: 303582 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.7481. Min Act: -0.1700
Data Index: 1904140 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.7793. Min Act: -0.1700
Data Index: 5606249 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.6856. Min Act: -0.1700
Data Index: 5769030 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.6856. Min Act: -0.1700
Data Index: 3593089 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.6543. Min Act: -0.1700
Data Index: 8046045 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.5918. Min Act: -0.1700
Data Index: 7440915 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.5606. Min Act: -0.1700
Data Index: 7097820 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.5606. Min Act: -0.1700
Data Index: 7537705 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.5606. Min Act: -0.1700
Data Index: 7185662 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.2168. Min Act: -0.1700
Data Index: 7916838 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.4981. Min Act: -0.1700
Data Index: 7883683 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.5293. Min Act: -0.1700
Data Index: 2229357 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.4981. Min Act: -0.1700
Data Index: 6442314 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.5606. Min Act: -0.1700
Data Index: 3314707 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0606. Min Range: -7.0606
Max Act: 6.4981. Min Act: -0.1700
Data Index: 5584353 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19