Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4651 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.9451. Min Act: -0.1700
Data Index: 8712691 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.7576. Min Act: -0.1700
Data Index: 3478201 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.6326. Min Act: -0.1700
Data Index: 1320926 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.6326. Min Act: -0.1700
Data Index: 527164 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.5701. Min Act: -0.1700
Data Index: 6194327 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.4763. Min Act: -0.1700
Data Index: 8106439 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.3201. Min Act: -0.1700
Data Index: 4815636 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.3513. Min Act: -0.1700
Data Index: 8626644 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.3201. Min Act: -0.1700
Data Index: 2413542 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.2888. Min Act: -0.1700
Data Index: 5345712 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.2888. Min Act: -0.1700
Data Index: 5230088 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.1951. Min Act: -0.1700
Data Index: 6168602 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.1951. Min Act: -0.1700
Data Index: 2761065 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.1638. Min Act: -0.1700
Data Index: 2087019 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.1638. Min Act: -0.1700
Data Index: 1366548 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.1013. Min Act: -0.1700
Data Index: 3836661 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.0701. Min Act: -0.1700
Data Index: 2729762 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.1013. Min Act: -0.1700
Data Index: 7998330 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.0388. Min Act: -0.1700
Data Index: 4926711 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9451. Min Range: -7.9451
Max Act: 7.1013. Min Act: -0.1700
Data Index: 5652972 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19