Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3776 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2034. Min Range: -5.2034
Max Act: 5.2034. Min Act: -0.1700
Data Index: 3666211 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2034. Min Range: -5.2034
Max Act: 5.1409. Min Act: -0.1700
Data Index: 7707224 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2034. Min Range: -5.2034
Max Act: 5.1097. Min Act: -0.1700
Data Index: 5550296 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2034. Min Range: -5.2034
Max Act: 5.0784. Min Act: -0.1700
Data Index: 3746905 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2034. Min Range: -5.2034
Max Act: 5.0472. Min Act: -0.1700
Data Index: 4912644 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2034. Min Range: -5.2034
Max Act: 5.0472. Min Act: -0.1700
Data Index: 2114819 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9847. Min Act: -0.1700
Data Index: 7655657 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9847. Min Act: -0.1700
Data Index: 7908992 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9847. Min Act: -0.1700
Data Index: 4575392 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9847. Min Act: -0.1700
Data Index: 4781559 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9847. Min Act: -0.1700
Data Index: 8241706 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9534. Min Act: -0.1700
Data Index: 684095 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9534. Min Act: -0.1700
Data Index: 2267385 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9534. Min Act: -0.1700
Data Index: 1187910 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9222. Min Act: -0.1700
Data Index: 8671388 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9222. Min Act: -0.1700
Data Index: 1375515 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.9222. Min Act: -0.1700
Data Index: 7893142 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.8909. Min Act: -0.1700
Data Index: 2161737 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.8909. Min Act: -0.1700
Data Index: 1510184 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2034. Min Range: -5.2034
Max Act: 4.8909. Min Act: -0.1700
Data Index: 6115661 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19