Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.4111. Min Act: -0.1698
Data Index: 4207014 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3486. Min Act: -0.1700
Data Index: 677399 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3486. Min Act: -0.1700
Data Index: 3926436 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3486. Min Act: -0.1700
Data Index: 7067249 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3486. Min Act: -0.1700
Data Index: 647645 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3486. Min Act: -0.1700
Data Index: 184612 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3486. Min Act: -0.1700
Data Index: 5099036 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3486. Min Act: -0.1700
Data Index: 3906168 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3486. Min Act: -0.1700
Data Index: 1448261 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3173. Min Act: -0.1700
Data Index: 3906167 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3173. Min Act: -0.1700
Data Index: 1528961 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.3173. Min Act: -0.1700
Data Index: 6813804 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.2861. Min Act: -0.1700
Data Index: 4793673 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.2861. Min Act: -0.1700
Data Index: 7355124 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.2548. Min Act: -0.1700
Data Index: 2611959 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.2861. Min Act: -0.1700
Data Index: 6505500 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.2548. Min Act: -0.1700
Data Index: 4228864 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.2548. Min Act: -0.1700
Data Index: 4903994 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.2548. Min Act: -0.1700
Data Index: 3523443 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4111. Min Range: -6.4111
Max Act: 6.2236. Min Act: -0.1700
Data Index: 6170996 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19