Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 91 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1689. Min Range: -11.1689
Max Act: 11.1689. Min Act: -0.1700
Data Index: 8488817 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1689. Min Range: -11.1689
Max Act: 11.0439. Min Act: -0.1700
Data Index: 7452337 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.9189. Min Act: -0.1700
Data Index: 1315078 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.6689. Min Act: -0.1700
Data Index: 8758775 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.6689. Min Act: -0.1700
Data Index: 2398680 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.5439. Min Act: -0.1700
Data Index: 640274 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.4814. Min Act: -0.1700
Data Index: 4198486 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.4189. Min Act: -0.1700
Data Index: 1386264 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.4189. Min Act: -0.1700
Data Index: 5338166 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.3564. Min Act: -0.1700
Data Index: 4722328 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.3564. Min Act: -0.1700
Data Index: 8051336 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.3564. Min Act: -0.1700
Data Index: 4374878 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.2939. Min Act: -0.1700
Data Index: 2703484 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.2939. Min Act: -0.1700
Data Index: 7582318 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.3564. Min Act: -0.1700
Data Index: 3672107 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.3564. Min Act: -0.1700
Data Index: 5320205 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.1689. Min Act: -0.1700
Data Index: 1149576 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.1689. Min Act: -0.1700
Data Index: 6305128 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.1064. Min Act: -0.1700
Data Index: 2731465 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1689. Min Range: -11.1689
Max Act: 10.1689. Min Act: -0.1700
Data Index: 8735088 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19