Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0909. Min Range: -7.0909
Max Act: 7.0909. Min Act: -0.1700
Data Index: 4253720 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0909. Min Range: -7.0909
Max Act: 7.0284. Min Act: -0.1700
Data Index: 7333291 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.9659. Min Act: -0.1699
Data Index: 8215358 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.9659. Min Act: -0.1700
Data Index: 3959755 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.9034. Min Act: -0.1700
Data Index: 7113414 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.8096. Min Act: -0.1700
Data Index: 8611310 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.8409. Min Act: -0.1700
Data Index: 5342998 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.8096. Min Act: -0.1700
Data Index: 198263 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.6846. Min Act: -0.1700
Data Index: 3825332 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.7159. Min Act: -0.1700
Data Index: 5275238 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.6846. Min Act: -0.1700
Data Index: 2913626 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.6846. Min Act: -0.1700
Data Index: 7848429 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.6846. Min Act: -0.1700
Data Index: 4960238 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.6534. Min Act: -0.1700
Data Index: 1758709 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.7159. Min Act: -0.1700
Data Index: 4903538 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.6221. Min Act: -0.1700
Data Index: 2504510 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.6846. Min Act: -0.1700
Data Index: 1288031 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.6846. Min Act: -0.1700
Data Index: 448168 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.5596. Min Act: -0.1700
Data Index: 6562991 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0909. Min Range: -7.0909
Max Act: 6.5909. Min Act: -0.1700
Data Index: 2320975 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19