Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 912 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1468. Min Range: -6.1468
Max Act: 6.1468. Min Act: -0.1700
Data Index: 970336 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.9281. Min Act: -0.1700
Data Index: 3432600 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.8343. Min Act: -0.1700
Data Index: 2656819 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.7406. Min Act: -0.1700
Data Index: 4320615 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.7406. Min Act: -0.1700
Data Index: 6037351 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.6781. Min Act: -0.1700
Data Index: 7423531 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.6468. Min Act: -0.1700
Data Index: 6248327 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.5843. Min Act: -0.1700
Data Index: 7521101 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.6156. Min Act: -0.1700
Data Index: 77072 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.5531. Min Act: -0.1700
Data Index: 8827358 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.5531. Min Act: -0.1700
Data Index: 8006312 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.5531. Min Act: -0.1700
Data Index: 2360259 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.5531. Min Act: -0.1700
Data Index: 7857815 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.5531. Min Act: -0.1700
Data Index: 5057368 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.4906. Min Act: -0.1700
Data Index: 5864757 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.5218. Min Act: -0.1700
Data Index: 2548204 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.5218. Min Act: -0.1700
Data Index: 7724752 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.5218. Min Act: -0.1700
Data Index: 3184645 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.4593. Min Act: -0.1700
Data Index: 560195 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1468. Min Range: -6.1468
Max Act: 5.4906. Min Act: -0.1700
Data Index: 463523 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19