Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0473. Min Range: -6.0473
Max Act: 6.0473. Min Act: -0.1700
Data Index: 7743849 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.9223. Min Act: -0.1700
Data Index: 1007122 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.8598. Min Act: -0.1700
Data Index: 106996 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.8911. Min Act: -0.1700
Data Index: 7258899 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.8286. Min Act: -0.1700
Data Index: 4396159 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.7661. Min Act: -0.1700
Data Index: 7997498 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.7973. Min Act: -0.1700
Data Index: 2440313 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.7661. Min Act: -0.1700
Data Index: 7902057 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.7661. Min Act: -0.1700
Data Index: 3734619 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.7348. Min Act: -0.1700
Data Index: 8374673 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.7348. Min Act: -0.1700
Data Index: 7265703 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.7348. Min Act: -0.1700
Data Index: 3661756 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.7036. Min Act: -0.1700
Data Index: 8830914 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.7036. Min Act: -0.1700
Data Index: 2524864 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.7036. Min Act: -0.1700
Data Index: 7428163 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.6723. Min Act: -0.1700
Data Index: 301695 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.6411. Min Act: -0.1700
Data Index: 8064915 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.6723. Min Act: -0.1700
Data Index: 8043795 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.6411. Min Act: -0.1700
Data Index: 183717 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0473. Min Range: -6.0473
Max Act: 5.6411. Min Act: -0.1700
Data Index: 7807237 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19