Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5483. Min Range: -7.5483
Max Act: 7.5483. Min Act: -0.1700
Data Index: 1209832 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5483. Min Range: -7.5483
Max Act: 7.2045. Min Act: -0.1700
Data Index: 1439005 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5483. Min Range: -7.5483
Max Act: 7.1733. Min Act: -0.1700
Data Index: 1819276 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5483. Min Range: -7.5483
Max Act: 7.1733. Min Act: -0.1700
Data Index: 6912718 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5483. Min Range: -7.5483
Max Act: 7.1733. Min Act: -0.1700
Data Index: 4721365 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5483. Min Range: -7.5483
Max Act: 7.1733. Min Act: -0.1700
Data Index: 1833440 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5483. Min Range: -7.5483
Max Act: 7.1420. Min Act: -0.1700
Data Index: 7447306 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5483. Min Range: -7.5483
Max Act: 7.1108. Min Act: -0.1700
Data Index: 3158650 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5483. Min Range: -7.5483
Max Act: 7.0483. Min Act: -0.1700
Data Index: 5791785 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5483. Min Range: -7.5483
Max Act: 7.0483. Min Act: -0.1700
Data Index: 1630042 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5483. Min Range: -7.5483
Max Act: 6.8920. Min Act: -0.1700
Data Index: 7120297 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5483. Min Range: -7.5483
Max Act: 6.8608. Min Act: -0.1700
Data Index: 4743964 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5483. Min Range: -7.5483
Max Act: 6.8608. Min Act: -0.1700
Data Index: 3062573 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5483. Min Range: -7.5483
Max Act: 6.8608. Min Act: -0.1700
Data Index: 3040072 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5483. Min Range: -7.5483
Max Act: 6.8608. Min Act: -0.1700
Data Index: 4193353 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5483. Min Range: -7.5483
Max Act: 6.8295. Min Act: -0.1700
Data Index: 4273630 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5483. Min Range: -7.5483
Max Act: 6.7983. Min Act: -0.1700
Data Index: 2320339 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5483. Min Range: -7.5483
Max Act: 6.7045. Min Act: -0.1700
Data Index: 5513076 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5483. Min Range: -7.5483
Max Act: 6.7358. Min Act: -0.1700
Data Index: 10924 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5483. Min Range: -7.5483
Max Act: 6.7045. Min Act: -0.1700
Data Index: 6591967 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19