Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3030. Min Range: -6.3030
Max Act: 6.3030. Min Act: -0.1700
Data Index: 1148648 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3030. Min Range: -6.3030
Max Act: 6.1467. Min Act: -0.1700
Data Index: 8447387 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3030. Min Range: -6.3030
Max Act: 6.0842. Min Act: -0.1700
Data Index: 4272075 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3030. Min Range: -6.3030
Max Act: 6.0530. Min Act: -0.1700
Data Index: 4369931 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.9905. Min Act: -0.1700
Data Index: 4369924 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.9905. Min Act: -0.1700
Data Index: 2898835 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.9592. Min Act: -0.1700
Data Index: 8703659 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.9280. Min Act: -0.1700
Data Index: 4079495 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.8655. Min Act: -0.1700
Data Index: 2385317 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.8030. Min Act: -0.1700
Data Index: 4524803 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.8342. Min Act: -0.1700
Data Index: 5832478 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.7717. Min Act: -0.1700
Data Index: 8114352 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.7405. Min Act: -0.1700
Data Index: 7147730 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.7405. Min Act: -0.1700
Data Index: 4696584 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.7092. Min Act: -0.1700
Data Index: 8674639 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.7092. Min Act: -0.1700
Data Index: 1846466 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.7092. Min Act: -0.1700
Data Index: 440105 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.6780. Min Act: -0.1700
Data Index: 7440502 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.6780. Min Act: -0.1700
Data Index: 5182646 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3030. Min Range: -6.3030
Max Act: 5.6467. Min Act: -0.1700
Data Index: 4677907 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19