Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2013 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3531. Min Range: -9.3531
Max Act: 9.3531. Min Act: -0.1700
Data Index: 5733913 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3531. Min Range: -9.3531
Max Act: 9.2281. Min Act: -0.1700
Data Index: 1197490 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3531. Min Range: -9.3531
Max Act: 9.2281. Min Act: -0.1700
Data Index: 8235383 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3531. Min Range: -9.3531
Max Act: 9.1031. Min Act: -0.1700
Data Index: 6449900 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3531. Min Range: -9.3531
Max Act: 9.1031. Min Act: -0.1700
Data Index: 6080299 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3531. Min Range: -9.3531
Max Act: 9.1031. Min Act: -0.1700
Data Index: 1212103 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3531. Min Range: -9.3531
Max Act: 9.0406. Min Act: -0.1700
Data Index: 115125 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3531. Min Range: -9.3531
Max Act: 9.0406. Min Act: -0.1700
Data Index: 8422739 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3531. Min Range: -9.3531
Max Act: 9.0406. Min Act: -0.1700
Data Index: 3666114 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3531. Min Range: -9.3531
Max Act: 9.0406. Min Act: -0.1700
Data Index: 1776687 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3531. Min Range: -9.3531
Max Act: 8.9781. Min Act: -0.1700
Data Index: 4369802 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3531. Min Range: -9.3531
Max Act: 8.9781. Min Act: -0.1700
Data Index: 4624612 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3531. Min Range: -9.3531
Max Act: 8.9781. Min Act: -0.1700
Data Index: 1762396 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3531. Min Range: -9.3531
Max Act: 8.8531. Min Act: -0.1700
Data Index: 2887782 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3531. Min Range: -9.3531
Max Act: 8.9156. Min Act: -0.1700
Data Index: 4064856 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3531. Min Range: -9.3531
Max Act: 8.9781. Min Act: -0.1700
Data Index: 8484855 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3531. Min Range: -9.3531
Max Act: 8.9156. Min Act: -0.1700
Data Index: 7432994 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3531. Min Range: -9.3531
Max Act: 8.8531. Min Act: -0.1700
Data Index: 696196 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3531. Min Range: -9.3531
Max Act: 8.7906. Min Act: -0.1700
Data Index: 2546066 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3531. Min Range: -9.3531
Max Act: 8.7906. Min Act: -0.1700
Data Index: 4175492 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19