Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.8184. Min Act: -0.1700
Data Index: 5447569 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.3809. Min Act: -0.1700
Data Index: 5623436 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.3184. Min Act: -0.1700
Data Index: 4042659 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.3184. Min Act: -0.1700
Data Index: 5133340 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.3184. Min Act: -0.1700
Data Index: 265058 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.2559. Min Act: -0.1700
Data Index: 1698904 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.2559. Min Act: -0.1700
Data Index: 1482679 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.2559. Min Act: -0.1700
Data Index: 8486857 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.1934. Min Act: -0.1700
Data Index: 448838 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.1309. Min Act: -0.1700
Data Index: 1508286 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.1309. Min Act: -0.1700
Data Index: 7885135 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.1309. Min Act: -0.1700
Data Index: 6688464 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.1309. Min Act: -0.1700
Data Index: 1820907 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.1309. Min Act: -0.1700
Data Index: 4511228 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.0684. Min Act: -0.1700
Data Index: 4895892 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.0684. Min Act: -0.1700
Data Index: 6155748 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.0684. Min Act: -0.1700
Data Index: 20686 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.0684. Min Act: -0.1700
Data Index: 4253566 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.0059. Min Act: -0.1700
Data Index: 5322320 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8184. Min Range: -9.8184
Max Act: 9.0059. Min Act: -0.1700
Data Index: 8147497 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19