Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.3402. Min Act: -0.1700
Data Index: 3343716 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.3089. Min Act: -0.1700
Data Index: 5482049 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.2777. Min Act: -0.1700
Data Index: 738520 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.1527. Min Act: -0.1700
Data Index: 381988 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.1214. Min Act: -0.1700
Data Index: 7490371 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.1527. Min Act: -0.1700
Data Index: 6391627 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.1527. Min Act: -0.1700
Data Index: 288351 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0902. Min Act: -0.1700
Data Index: 2191522 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0902. Min Act: -0.1700
Data Index: 1836107 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0902. Min Act: -0.1700
Data Index: 4849884 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0902. Min Act: -0.1700
Data Index: 7440472 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0589. Min Act: -0.1700
Data Index: 4307324 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0589. Min Act: -0.1700
Data Index: 6070505 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0902. Min Act: -0.1700
Data Index: 6303560 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0589. Min Act: -0.1700
Data Index: 7021869 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0589. Min Act: -0.1700
Data Index: 2314660 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0902. Min Act: -0.1700
Data Index: 6530789 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0277. Min Act: -0.1700
Data Index: 2335852 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0589. Min Act: -0.1700
Data Index: 7239967 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3402. Min Range: -5.3402
Max Act: 5.0277. Min Act: -0.1700
Data Index: 3242044 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19