Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2031 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2183. Min Range: -2.2183
Max Act: 2.2183. Min Act: -0.1700
Data Index: 3233353 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2183. Min Range: -2.2183
Max Act: 2.0345. Min Act: -0.1700
Data Index: 6056857 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2183. Min Range: -2.2183
Max Act: 2.0176. Min Act: -0.1700
Data Index: 7702603 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2183. Min Range: -2.2183
Max Act: 2.0176. Min Act: -0.1700
Data Index: 6036294 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2183. Min Range: -2.2183
Max Act: 2.0176. Min Act: -0.1700
Data Index: 4581103 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.9839. Min Act: -0.1700
Data Index: 7012805 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.9499. Min Act: -0.1700
Data Index: 4559705 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.9330. Min Act: -0.1700
Data Index: 1443688 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.9159. Min Act: -0.1700
Data Index: 4790164 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.9330. Min Act: -0.1700
Data Index: 8223127 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.9159. Min Act: -0.1700
Data Index: 4495916 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.8989. Min Act: -0.1700
Data Index: 4456307 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.8989. Min Act: -0.1700
Data Index: 763129 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.8989. Min Act: -0.1700
Data Index: 4563218 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.8989. Min Act: -0.1700
Data Index: 6210891 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.8989. Min Act: -0.1700
Data Index: 7149283 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.8647. Min Act: -0.1700
Data Index: 2289853 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.8647. Min Act: -0.1700
Data Index: 85940 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.8818. Min Act: -0.1700
Data Index: 677080 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2183. Min Range: -2.2183
Max Act: 1.8818. Min Act: -0.1700
Data Index: 295108 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19