Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 455 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.5529. Min Act: -0.1700
Data Index: 6026604 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.4904. Min Act: -0.1700
Data Index: 6667124 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.3967. Min Act: -0.1700
Data Index: 5409665 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.0842. Min Act: -0.1700
Data Index: 7219443 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.0842. Min Act: -0.1700
Data Index: 6201140 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.1154. Min Act: -0.1700
Data Index: 5332593 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.0217. Min Act: -0.1700
Data Index: 5043030 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.0217. Min Act: -0.1700
Data Index: 4430226 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.9592. Min Act: -0.1700
Data Index: 1443357 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.9279. Min Act: -0.1700
Data Index: 7089858 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.8967. Min Act: -0.1700
Data Index: 6519124 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.8654. Min Act: -0.1700
Data Index: 5364500 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.8342. Min Act: -0.1700
Data Index: 5619931 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.8029. Min Act: -0.1700
Data Index: 3435433 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.7717. Min Act: -0.1700
Data Index: 2330397 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.7404. Min Act: -0.1700
Data Index: 2812292 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.6779. Min Act: -0.1700
Data Index: 7789884 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.6779. Min Act: -0.1700
Data Index: 957021 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.6779. Min Act: -0.1700
Data Index: 8134436 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.6467. Min Act: -0.1700
Data Index: 1709707 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19