Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1018. Min Range: -3.1018
Max Act: 3.1018. Min Act: -0.1700
Data Index: 3674405 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1018. Min Range: -3.1018
Max Act: 3.0071. Min Act: -0.1697
Data Index: 3040005 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1018. Min Range: -3.1018
Max Act: 3.0071. Min Act: -0.1700
Data Index: 1319358 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.9122. Min Act: -0.1700
Data Index: 5493210 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.8646. Min Act: -0.1700
Data Index: 5793686 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.8328. Min Act: -0.1700
Data Index: 266421 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.8487. Min Act: -0.1700
Data Index: 1998167 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.8169. Min Act: -0.1700
Data Index: 5925223 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.7850. Min Act: -0.1700
Data Index: 1643718 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.7850. Min Act: -0.1699
Data Index: 4244649 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.7691. Min Act: -0.1689
Data Index: 8580966 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.7372. Min Act: -0.1700
Data Index: 5556075 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.7212. Min Act: -0.1699
Data Index: 8671712 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.7212. Min Act: -0.1698
Data Index: 2127390 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.7052. Min Act: -0.1700
Data Index: 3967799 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.7052. Min Act: -0.1700
Data Index: 1709716 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.7052. Min Act: -0.1697
Data Index: 8002493 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.6892. Min Act: -0.1700
Data Index: 8170499 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.6732. Min Act: -0.1700
Data Index: 4561556 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1018. Min Range: -3.1018
Max Act: 2.6732. Min Act: -0.1700
Data Index: 1088064 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19