Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2779 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.4140. Min Act: -0.1700
Data Index: 3379395 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.8826. Min Act: -0.1700
Data Index: 6222471 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.8513. Min Act: -0.1700
Data Index: 6259879 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.8826. Min Act: -0.1700
Data Index: 3892994 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.8513. Min Act: -0.1700
Data Index: 7592006 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.8200. Min Act: -0.1700
Data Index: 1957226 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.8200. Min Act: -0.1700
Data Index: 6955724 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.7888. Min Act: -0.1700
Data Index: 7574629 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.7106. Min Act: -0.1700
Data Index: 4815120 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6793. Min Act: -0.1700
Data Index: 3789978 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6793. Min Act: -0.1700
Data Index: 4213108 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6480. Min Act: -0.1700
Data Index: 1957227 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6793. Min Act: -0.1700
Data Index: 5415475 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6323. Min Act: -0.1700
Data Index: 1647470 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6323. Min Act: -0.1700
Data Index: 4581652 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6167. Min Act: -0.1700
Data Index: 3911412 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6167. Min Act: -0.1700
Data Index: 4581651 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6167. Min Act: -0.1700
Data Index: 1791554 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6323. Min Act: -0.1700
Data Index: 5254328 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4140. Min Range: -4.4140
Max Act: 3.6011. Min Act: -0.1700
Data Index: 295076 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19