Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5868. Min Range: -6.5868
Max Act: 6.5868. Min Act: -0.1700
Data Index: 3168917 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5868. Min Range: -6.5868
Max Act: 6.3680. Min Act: -0.1700
Data Index: 2185411 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5868. Min Range: -6.5868
Max Act: 6.1493. Min Act: -0.1700
Data Index: 8256639 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5868. Min Range: -6.5868
Max Act: 6.1805. Min Act: -0.1700
Data Index: 1760677 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5868. Min Range: -6.5868
Max Act: 6.1180. Min Act: -0.1700
Data Index: 368078 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.9930. Min Act: -0.1700
Data Index: 2350961 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.8993. Min Act: -0.1700
Data Index: 7062461 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.8993. Min Act: -0.1700
Data Index: 1769524 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.8680. Min Act: -0.1700
Data Index: 7101852 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.8368. Min Act: -0.1700
Data Index: 4441470 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.7430. Min Act: -0.1700
Data Index: 8767784 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.8368. Min Act: -0.1700
Data Index: 2293896 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.8055. Min Act: -0.1700
Data Index: 3756547 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.7743. Min Act: -0.1700
Data Index: 3384925 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.7743. Min Act: -0.1700
Data Index: 5676957 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.7743. Min Act: -0.1700
Data Index: 8209711 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.7430. Min Act: -0.1700
Data Index: 7826540 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.7743. Min Act: -0.1700
Data Index: 1003193 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.7743. Min Act: -0.1700
Data Index: 6890359 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5868. Min Range: -6.5868
Max Act: 5.7430. Min Act: -0.1700
Data Index: 7017394 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19