Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 429 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.7414. Min Act: -0.1700
Data Index: 190925 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.6632. Min Act: -0.1700
Data Index: 5589668 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.6319. Min Act: -0.1700
Data Index: 4695195 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.6006. Min Act: -0.1700
Data Index: 984300 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.6006. Min Act: -0.1700
Data Index: 320568 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5850. Min Act: -0.1700
Data Index: 5743851 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5850. Min Act: -0.1700
Data Index: 4329007 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5850. Min Act: -0.1700
Data Index: 5003060 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5693. Min Act: -0.1700
Data Index: 7113047 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5693. Min Act: -0.1700
Data Index: 6915713 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5380. Min Act: -0.1700
Data Index: 2487813 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5380. Min Act: -0.1700
Data Index: 7636429 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5380. Min Act: -0.1700
Data Index: 1414908 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5223. Min Act: -0.1700
Data Index: 3697741 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5067. Min Act: -0.1700
Data Index: 8301191 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5067. Min Act: -0.1700
Data Index: 8731067 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.4753. Min Act: -0.1700
Data Index: 5403409 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.5067. Min Act: -0.1700
Data Index: 6423583 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.4597. Min Act: -0.1700
Data Index: 6946832 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7414. Min Range: -3.7414
Max Act: 3.4753. Min Act: -0.1700
Data Index: 5191707 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19