Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2479 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3898. Min Range: -6.3898
Max Act: 6.3898. Min Act: -0.1700
Data Index: 1956360 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3898. Min Range: -6.3898
Max Act: 6.1711. Min Act: -0.1700
Data Index: 4711869 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3898. Min Range: -6.3898
Max Act: 6.1398. Min Act: -0.1700
Data Index: 6596826 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3898. Min Range: -6.3898
Max Act: 6.1398. Min Act: -0.1700
Data Index: 1607211 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3898. Min Range: -6.3898
Max Act: 6.1086. Min Act: -0.1700
Data Index: 654217 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.9523. Min Act: -0.1700
Data Index: 737337 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.9523. Min Act: -0.1700
Data Index: 1063723 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.9211. Min Act: -0.1700
Data Index: 4269719 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.9211. Min Act: -0.1700
Data Index: 5474828 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.8898. Min Act: -0.1700
Data Index: 5519718 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.8898. Min Act: -0.1700
Data Index: 5775699 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.8586. Min Act: -0.1700
Data Index: 5242269 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.8273. Min Act: -0.1700
Data Index: 2033709 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.8898. Min Act: -0.1700
Data Index: 4158992 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.8586. Min Act: -0.1700
Data Index: 4269113 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.8273. Min Act: -0.1700
Data Index: 4682874 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.8273. Min Act: -0.1700
Data Index: 4857646 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.7961. Min Act: -0.1700
Data Index: 6898851 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.7961. Min Act: -0.1700
Data Index: 2645399 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3898. Min Range: -6.3898
Max Act: 5.7961. Min Act: -0.1700
Data Index: 4019922 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19