Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1757 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0538. Min Range: -2.0538
Max Act: 2.0538. Min Act: -0.1700
Data Index: 8078502 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0538. Min Range: -2.0538
Max Act: 2.0369. Min Act: -0.1699
Data Index: 5734579 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0538. Min Range: -2.0538
Max Act: 2.0201. Min Act: -0.1700
Data Index: 4924888 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0538. Min Range: -2.0538
Max Act: 2.0032. Min Act: -0.1700
Data Index: 4275745 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0538. Min Range: -2.0538
Max Act: 2.0032. Min Act: -0.1700
Data Index: 547871 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0538. Min Range: -2.0538
Max Act: 2.0032. Min Act: -0.1700
Data Index: 3911460 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0538. Min Range: -2.0538
Max Act: 1.9863. Min Act: -0.1700
Data Index: 1656542 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0538. Min Range: -2.0538
Max Act: 2.0032. Min Act: -0.1700
Data Index: 3115673 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0538. Min Range: -2.0538
Max Act: 2.0201. Min Act: -0.1700
Data Index: 5414073 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0538. Min Range: -2.0538
Max Act: 2.0032. Min Act: -0.1700
Data Index: 246359 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0538. Min Range: -2.0538
Max Act: 1.9863. Min Act: -0.1700
Data Index: 1730686 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0538. Min Range: -2.0538
Max Act: 1.9863. Min Act: -0.1700
Data Index: 1971377 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0538. Min Range: -2.0538
Max Act: 1.9863. Min Act: -0.1700
Data Index: 4237631 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0538. Min Range: -2.0538
Max Act: 1.9863. Min Act: -0.1700
Data Index: 2366162 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0538. Min Range: -2.0538
Max Act: 2.0032. Min Act: -0.1700
Data Index: 4609531 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0538. Min Range: -2.0538
Max Act: 1.9694. Min Act: -0.1700
Data Index: 2332328 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0538. Min Range: -2.0538
Max Act: 1.9524. Min Act: -0.1700
Data Index: 4053215 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0538. Min Range: -2.0538
Max Act: 1.9694. Min Act: -0.1700
Data Index: 7249495 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0538. Min Range: -2.0538
Max Act: 1.9694. Min Act: -0.1700
Data Index: 7755433 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0538. Min Range: -2.0538
Max Act: 1.9694. Min Act: -0.1700
Data Index: 3509159 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19