Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 805 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2104. Min Range: -4.2104
Max Act: 4.2104. Min Act: -0.1700
Data Index: 1468693 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2104. Min Range: -4.2104
Max Act: 4.1791. Min Act: -0.1700
Data Index: 724322 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2104. Min Range: -4.2104
Max Act: 4.1166. Min Act: -0.1700
Data Index: 950486 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2104. Min Range: -4.2104
Max Act: 4.0541. Min Act: -0.1700
Data Index: 5527779 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2104. Min Range: -4.2104
Max Act: 4.0541. Min Act: -0.1700
Data Index: 4496720 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2104. Min Range: -4.2104
Max Act: 4.0541. Min Act: -0.1700
Data Index: 3000027 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2104. Min Range: -4.2104
Max Act: 4.0541. Min Act: -0.1700
Data Index: 8305668 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.9291. Min Act: -0.1699
Data Index: 3380739 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.9291. Min Act: -0.1700
Data Index: 5345607 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.9291. Min Act: -0.1700
Data Index: 3338306 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.9291. Min Act: -0.1700
Data Index: 5304264 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.9291. Min Act: -0.1700
Data Index: 6198394 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.9291. Min Act: -0.1700
Data Index: 382395 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.9291. Min Act: -0.1700
Data Index: 3501424 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.8978. Min Act: -0.1693
Data Index: 532748 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.8665. Min Act: -0.1700
Data Index: 3067352 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.8665. Min Act: -0.1700
Data Index: 6460592 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.8978. Min Act: -0.1700
Data Index: 5547002 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.8665. Min Act: -0.1700
Data Index: 4496729 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2104. Min Range: -4.2104
Max Act: 3.8353. Min Act: -0.1700
Data Index: 2911780 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19