Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.8666. Min Act: -0.1700
Data Index: 4171927 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.8066. Min Act: -0.1700
Data Index: 8758442 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.7721. Min Act: -0.1700
Data Index: 3824190 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.7721. Min Act: -0.1700
Data Index: 8676502 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.7549. Min Act: -0.1700
Data Index: 8524677 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.7290. Min Act: -0.1700
Data Index: 6843140 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.7203. Min Act: -0.1700
Data Index: 2110205 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.7116. Min Act: -0.1700
Data Index: 4991480 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.7116. Min Act: -0.1699
Data Index: 8695239 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.7030. Min Act: -0.1700
Data Index: 2911600 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.6943. Min Act: -0.1700
Data Index: 7955142 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.7030. Min Act: -0.1700
Data Index: 8695242 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.6943. Min Act: -0.1700
Data Index: 3953038 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.6943. Min Act: -0.1700
Data Index: 8695241 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.6943. Min Act: -0.1700
Data Index: 7913438 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.6769. Min Act: -0.1698
Data Index: 7342677 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.6856. Min Act: -0.1700
Data Index: 968880 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.6769. Min Act: -0.1700
Data Index: 4267063 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.6769. Min Act: -0.1700
Data Index: 2169518 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8666. Min Range: -1.8666
Max Act: 1.6682. Min Act: -0.1700
Data Index: 5392304 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19