Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.4417. Min Act: -0.1700
Data Index: 3592948 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.4104. Min Act: -0.1700
Data Index: 3592952 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.3792. Min Act: -0.1700
Data Index: 6091389 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.3479. Min Act: -0.1700
Data Index: 2094231 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.3479. Min Act: -0.1700
Data Index: 4525061 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.3167. Min Act: -0.1700
Data Index: 8389192 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.3167. Min Act: -0.1700
Data Index: 7894336 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.2854. Min Act: -0.1700
Data Index: 4777484 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.2854. Min Act: -0.1700
Data Index: 917743 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.2854. Min Act: -0.1700
Data Index: 6796599 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.2542. Min Act: -0.1700
Data Index: 3392539 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.2229. Min Act: -0.1700
Data Index: 7291663 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.2542. Min Act: -0.1700
Data Index: 8791331 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.2542. Min Act: -0.1700
Data Index: 3662883 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.2542. Min Act: -0.1700
Data Index: 858334 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.2229. Min Act: -0.1700
Data Index: 2287656 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.1917. Min Act: -0.1700
Data Index: 8519778 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.1917. Min Act: -0.1700
Data Index: 3840886 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.1604. Min Act: -0.1700
Data Index: 2640337 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4417. Min Range: -5.4417
Max Act: 5.1917. Min Act: -0.1700
Data Index: 8493081 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19