Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3678. Min Range: -8.3678
Max Act: 8.3678. Min Act: -0.1700
Data Index: 221599 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3678. Min Range: -8.3678
Max Act: 8.0553. Min Act: -0.1700
Data Index: 4745321 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.7428. Min Act: -0.1700
Data Index: 1333486 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.7115. Min Act: -0.1700
Data Index: 1682868 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.7428. Min Act: -0.1700
Data Index: 4562875 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.7115. Min Act: -0.1700
Data Index: 6013493 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.6178. Min Act: -0.1700
Data Index: 6453190 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.5865. Min Act: -0.1700
Data Index: 947681 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.5553. Min Act: -0.1700
Data Index: 4594886 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.5553. Min Act: -0.1700
Data Index: 6384348 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.5865. Min Act: -0.1700
Data Index: 5313044 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.5240. Min Act: -0.1700
Data Index: 4164035 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.5240. Min Act: -0.1700
Data Index: 7178710 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.4928. Min Act: -0.1700
Data Index: 6322152 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.4615. Min Act: -0.1700
Data Index: 6364422 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.4303. Min Act: -0.1700
Data Index: 6106603 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.4615. Min Act: -0.1700
Data Index: 763128 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.4928. Min Act: -0.1700
Data Index: 2619031 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.4615. Min Act: -0.1700
Data Index: 653398 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3678. Min Range: -8.3678
Max Act: 7.4615. Min Act: -0.1700
Data Index: 1725502 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19