Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4554. Min Range: -7.4554
Max Act: 7.4554. Min Act: -0.1700
Data Index: 6034535 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4554. Min Range: -7.4554
Max Act: 7.4554. Min Act: -0.1700
Data Index: 412770 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4554. Min Range: -7.4554
Max Act: 7.3929. Min Act: -0.1700
Data Index: 4727507 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4554. Min Range: -7.4554
Max Act: 7.2679. Min Act: -0.1700
Data Index: 4474716 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4554. Min Range: -7.4554
Max Act: 7.2054. Min Act: -0.1700
Data Index: 7220799 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4554. Min Range: -7.4554
Max Act: 7.1429. Min Act: -0.1700
Data Index: 1108885 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4554. Min Range: -7.4554
Max Act: 7.1116. Min Act: -0.1700
Data Index: 8777496 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.9866. Min Act: -0.1700
Data Index: 4727508 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.9554. Min Act: -0.1700
Data Index: 4979640 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.9554. Min Act: -0.1700
Data Index: 6501668 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.9554. Min Act: -0.1700
Data Index: 38022 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.9241. Min Act: -0.1700
Data Index: 4477146 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.7991. Min Act: -0.1700
Data Index: 4589964 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.7679. Min Act: -0.1700
Data Index: 4349499 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.7991. Min Act: -0.1700
Data Index: 6506015 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.7679. Min Act: -0.1700
Data Index: 6441928 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.7679. Min Act: -0.1700
Data Index: 6398640 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.7679. Min Act: -0.1700
Data Index: 3629682 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.7054. Min Act: -0.1700
Data Index: 3446681 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4554. Min Range: -7.4554
Max Act: 6.7366. Min Act: -0.1700
Data Index: 3911162 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19