Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5749 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0804. Min Range: -7.0804
Max Act: 7.0804. Min Act: -0.1700
Data Index: 6296823 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0804. Min Range: -7.0804
Max Act: 7.0491. Min Act: -0.1700
Data Index: 3999421 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.9866. Min Act: -0.1700
Data Index: 7585686 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.9866. Min Act: -0.1700
Data Index: 4402659 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.9554. Min Act: -0.1700
Data Index: 4591902 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.9554. Min Act: -0.1700
Data Index: 4029351 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.9241. Min Act: -0.1700
Data Index: 5000272 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.9241. Min Act: -0.1700
Data Index: 5217078 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.8929. Min Act: -0.1700
Data Index: 281787 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.8929. Min Act: -0.1700
Data Index: 6464291 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.8616. Min Act: -0.1700
Data Index: 3892441 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.8616. Min Act: -0.1700
Data Index: 2150243 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.8616. Min Act: -0.1700
Data Index: 55965 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.8304. Min Act: -0.1700
Data Index: 4391508 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.8304. Min Act: -0.1700
Data Index: 1184288 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.8304. Min Act: -0.1700
Data Index: 2849055 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.7679. Min Act: -0.1700
Data Index: 7993842 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.7991. Min Act: -0.1700
Data Index: 215696 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.7991. Min Act: -0.1700
Data Index: 3699189 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0804. Min Range: -7.0804
Max Act: 6.7991. Min Act: -0.1700
Data Index: 532676 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19