Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3190. Min Range: -6.3190
Max Act: 6.3190. Min Act: -0.1700
Data Index: 2053886 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3190. Min Range: -6.3190
Max Act: 6.1940. Min Act: -0.1700
Data Index: 4331894 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3190. Min Range: -6.3190
Max Act: 6.1315. Min Act: -0.1700
Data Index: 2152184 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3190. Min Range: -6.3190
Max Act: 6.1628. Min Act: -0.1700
Data Index: 5968587 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3190. Min Range: -6.3190
Max Act: 6.0690. Min Act: -0.1700
Data Index: 243725 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.9440. Min Act: -0.1700
Data Index: 2412324 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.8815. Min Act: -0.1700
Data Index: 2608215 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.9128. Min Act: -0.1700
Data Index: 325091 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.8815. Min Act: -0.1700
Data Index: 5655887 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.8503. Min Act: -0.1700
Data Index: 1051020 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.8503. Min Act: -0.1700
Data Index: 2422052 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.8503. Min Act: -0.1700
Data Index: 2120151 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.8190. Min Act: -0.1700
Data Index: 4375272 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.7878. Min Act: -0.1700
Data Index: 5915623 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.7565. Min Act: -0.1700
Data Index: 1284197 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.7565. Min Act: -0.1700
Data Index: 7025647 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.7878. Min Act: -0.1700
Data Index: 5229463 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.7878. Min Act: -0.1700
Data Index: 7525823 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.7253. Min Act: -0.1700
Data Index: 1830101 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3190. Min Range: -6.3190
Max Act: 5.6940. Min Act: -0.1700
Data Index: 4536036 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19