Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.9537. Min Act: -0.1700
Data Index: 3281579 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.9197. Min Act: -0.1700
Data Index: 5240729 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8429. Min Act: -0.1700
Data Index: 1800844 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8429. Min Act: -0.1700
Data Index: 696235 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8257. Min Act: -0.1700
Data Index: 6350840 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8343. Min Act: -0.1700
Data Index: 3109670 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8257. Min Act: -0.1700
Data Index: 7667095 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8171. Min Act: -0.1700
Data Index: 3025286 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8171. Min Act: -0.1700
Data Index: 4530944 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8171. Min Act: -0.1700
Data Index: 1800846 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8171. Min Act: -0.1700
Data Index: 464473 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8171. Min Act: -0.1700
Data Index: 8389934 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8171. Min Act: -0.1700
Data Index: 2051949 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8085. Min Act: -0.1698
Data Index: 1845933 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.8085. Min Act: -0.1700
Data Index: 6131853 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.7999. Min Act: -0.1700
Data Index: 2490399 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.7999. Min Act: -0.1700
Data Index: 7578331 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.7913. Min Act: -0.1700
Data Index: 4195089 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.7913. Min Act: -0.1700
Data Index: 736276 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9537. Min Range: -1.9537
Max Act: 1.7913. Min Act: -0.1700
Data Index: 6355110 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19