Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5999. Min Act: -0.1700
Data Index: 4710979 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.6156. Min Act: -0.1700
Data Index: 5975762 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5843. Min Act: -0.1700
Data Index: 5902646 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5530. Min Act: -0.1700
Data Index: 6177075 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5686. Min Act: -0.1700
Data Index: 3160335 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5530. Min Act: -0.1700
Data Index: 3575054 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5373. Min Act: -0.1700
Data Index: 621769 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5217. Min Act: -0.1700
Data Index: 6372695 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5373. Min Act: -0.1700
Data Index: 1726353 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5217. Min Act: -0.1700
Data Index: 8005742 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5060. Min Act: -0.1700
Data Index: 5585024 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5060. Min Act: -0.1700
Data Index: 949636 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.4903. Min Act: -0.1700
Data Index: 725355 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.5060. Min Act: -0.1700
Data Index: 6411630 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.4590. Min Act: -0.1700
Data Index: 74373 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.4433. Min Act: -0.1700
Data Index: 4952361 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.4747. Min Act: -0.1700
Data Index: 4025734 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.4433. Min Act: -0.1700
Data Index: 798160 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.4747. Min Act: -0.1700
Data Index: 1129657 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6156. Min Range: -3.6156
Max Act: 3.4433. Min Act: -0.1700
Data Index: 6241751 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19