Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 807 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4435. Min Range: -5.4435
Max Act: 5.4435. Min Act: -0.1700
Data Index: 4175067 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4435. Min Range: -5.4435
Max Act: 5.3498. Min Act: -0.1700
Data Index: 3601969 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4435. Min Range: -5.4435
Max Act: 5.2873. Min Act: -0.1700
Data Index: 5159107 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4435. Min Range: -5.4435
Max Act: 5.1935. Min Act: -0.1700
Data Index: 5996490 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4435. Min Range: -5.4435
Max Act: 5.1623. Min Act: -0.1700
Data Index: 6092127 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4435. Min Range: -5.4435
Max Act: 5.0373. Min Act: -0.1700
Data Index: 8078870 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.9748. Min Act: -0.1700
Data Index: 6385446 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.9123. Min Act: -0.1700
Data Index: 3342722 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.8498. Min Act: -0.1700
Data Index: 701464 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.8498. Min Act: -0.1700
Data Index: 8229925 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.8185. Min Act: -0.1700
Data Index: 4113813 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.7873. Min Act: -0.1700
Data Index: 6674356 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.7873. Min Act: -0.1700
Data Index: 4143829 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.7873. Min Act: -0.1700
Data Index: 3342725 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.7873. Min Act: -0.1700
Data Index: 1865028 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.7560. Min Act: -0.1700
Data Index: 2697413 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.7248. Min Act: -0.1700
Data Index: 5421807 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.7248. Min Act: -0.1700
Data Index: 496990 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.6935. Min Act: -0.1700
Data Index: 472880 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4435. Min Range: -5.4435
Max Act: 4.6935. Min Act: -0.1700
Data Index: 2822587 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19