Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4061 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.6236. Min Act: -0.1700
Data Index: 8123729 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.3736. Min Act: -0.1700
Data Index: 4517171 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.3110. Min Act: -0.1700
Data Index: 3018164 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.3110. Min Act: -0.1700
Data Index: 4999587 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.2173. Min Act: -0.1700
Data Index: 4886369 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.1548. Min Act: -0.1700
Data Index: 6391891 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.1235. Min Act: -0.1700
Data Index: 3375929 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.0610. Min Act: -0.1700
Data Index: 3527373 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.0610. Min Act: -0.1700
Data Index: 7358466 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.0298. Min Act: -0.1700
Data Index: 7704927 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.0298. Min Act: -0.1700
Data Index: 562390 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.0298. Min Act: -0.1700
Data Index: 2799464 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6236. Min Range: -4.6236
Max Act: 4.0298. Min Act: -0.1700
Data Index: 7379770 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6236. Min Range: -4.6236
Max Act: 3.9672. Min Act: -0.1700
Data Index: 3503336 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6236. Min Range: -4.6236
Max Act: 3.9672. Min Act: -0.1700
Data Index: 631433 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6236. Min Range: -4.6236
Max Act: 3.9360. Min Act: -0.1700
Data Index: 450460 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6236. Min Range: -4.6236
Max Act: 3.9047. Min Act: -0.1700
Data Index: 3650097 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6236. Min Range: -4.6236
Max Act: 3.9360. Min Act: -0.1700
Data Index: 518098 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6236. Min Range: -4.6236
Max Act: 3.9360. Min Act: -0.1700
Data Index: 3521659 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6236. Min Range: -4.6236
Max Act: 3.9672. Min Act: -0.1700
Data Index: 4109364 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19