Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.8332. Min Act: -0.1700
Data Index: 740708 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.7395. Min Act: -0.1700
Data Index: 1835370 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.6145. Min Act: -0.1700
Data Index: 417369 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.6145. Min Act: -0.1700
Data Index: 2374733 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.6145. Min Act: -0.1700
Data Index: 4463847 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4895. Min Act: -0.1700
Data Index: 4733983 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.5207. Min Act: -0.1700
Data Index: 2019013 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.5832. Min Act: -0.1700
Data Index: 902456 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4895. Min Act: -0.1700
Data Index: 1473852 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4895. Min Act: -0.1700
Data Index: 4347247 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4582. Min Act: -0.1700
Data Index: 6666149 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4270. Min Act: -0.1700
Data Index: 4671129 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4895. Min Act: -0.1700
Data Index: 1692760 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4895. Min Act: -0.1700
Data Index: 522096 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4582. Min Act: -0.1700
Data Index: 4631701 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4270. Min Act: -0.1700
Data Index: 895240 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4270. Min Act: -0.1700
Data Index: 6554829 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4270. Min Act: -0.1700
Data Index: 4347246 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.3957. Min Act: -0.1700
Data Index: 4891976 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8332. Min Range: -5.8332
Max Act: 5.4270. Min Act: -0.1700
Data Index: 4891975 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19