Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 86 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0424. Min Range: -5.0424
Max Act: 5.0112. Min Act: -0.1700
Data Index: 5531463 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0424. Min Range: -5.0424
Max Act: 5.0424. Min Act: -0.1700
Data Index: 5536029 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.9174. Min Act: -0.1700
Data Index: 2929491 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.8862. Min Act: -0.1700
Data Index: 4469366 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.9174. Min Act: -0.1700
Data Index: 8153139 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.8549. Min Act: -0.1700
Data Index: 3667103 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.8862. Min Act: -0.1700
Data Index: 8359228 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.8237. Min Act: -0.1700
Data Index: 1494398 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7924. Min Act: -0.1700
Data Index: 7685043 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7612. Min Act: -0.1700
Data Index: 4716857 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7612. Min Act: -0.1700
Data Index: 7195159 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7612. Min Act: -0.1700
Data Index: 5145572 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7299. Min Act: -0.1700
Data Index: 1707755 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7612. Min Act: -0.1700
Data Index: 5218731 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7612. Min Act: -0.1700
Data Index: 8663513 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7924. Min Act: -0.1700
Data Index: 7806015 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7612. Min Act: -0.1700
Data Index: 6415697 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7924. Min Act: -0.1700
Data Index: 4220080 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.6987. Min Act: -0.1700
Data Index: 6711973 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0424. Min Range: -5.0424
Max Act: 4.7299. Min Act: -0.1700
Data Index: 5776087 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19