Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.6152. Min Act: -0.1687
Data Index: 149357 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.5977. Min Act: -0.1638
Data Index: 4112948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.5102. Min Act: -0.1700
Data Index: 774867 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.5014. Min Act: -0.1700
Data Index: 2450737 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4838. Min Act: -0.1700
Data Index: 387595 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4750. Min Act: -0.1700
Data Index: 8624634 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4750. Min Act: -0.1700
Data Index: 3023156 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4662. Min Act: -0.1695
Data Index: 5113178 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4662. Min Act: -0.1700
Data Index: 6242795 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4575. Min Act: -0.1686
Data Index: 5070560 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4575. Min Act: -0.1700
Data Index: 6631346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4487. Min Act: -0.1629
Data Index: 3175974 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4311. Min Act: -0.1693
Data Index: 2707047 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4575. Min Act: -0.1682
Data Index: 157671 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4487. Min Act: -0.1700
Data Index: 2450735 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4399. Min Act: -0.1694
Data Index: 6242798 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4399. Min Act: -0.1696
Data Index: 8025280 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4223. Min Act: -0.1698
Data Index: 6242797 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4311. Min Act: -0.1700
Data Index: 5308409 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6152. Min Range: -1.6152
Max Act: 1.4399. Min Act: -0.1700
Data Index: 6019519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19