Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5626 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2073. Min Range: -5.2073
Max Act: 5.2073. Min Act: -0.1700
Data Index: 5545838 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2073. Min Range: -5.2073
Max Act: 5.1448. Min Act: -0.1700
Data Index: 3336053 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2073. Min Range: -5.2073
Max Act: 5.1448. Min Act: -0.1700
Data Index: 401616 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2073. Min Range: -5.2073
Max Act: 5.0823. Min Act: -0.1700
Data Index: 6113039 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2073. Min Range: -5.2073
Max Act: 5.1136. Min Act: -0.1700
Data Index: 3471233 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2073. Min Range: -5.2073
Max Act: 5.0823. Min Act: -0.1700
Data Index: 3712546 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2073. Min Range: -5.2073
Max Act: 5.0511. Min Act: -0.1700
Data Index: 1104206 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2073. Min Range: -5.2073
Max Act: 5.0511. Min Act: -0.1700
Data Index: 940269 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2073. Min Range: -5.2073
Max Act: 5.0511. Min Act: -0.1700
Data Index: 2668265 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2073. Min Range: -5.2073
Max Act: 5.0198. Min Act: -0.1700
Data Index: 975835 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2073. Min Range: -5.2073
Max Act: 4.9573. Min Act: -0.1700
Data Index: 7964223 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2073. Min Range: -5.2073
Max Act: 4.9886. Min Act: -0.1700
Data Index: 2066073 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2073. Min Range: -5.2073
Max Act: 4.9886. Min Act: -0.1700
Data Index: 787109 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2073. Min Range: -5.2073
Max Act: 4.9573. Min Act: -0.1700
Data Index: 8739272 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2073. Min Range: -5.2073
Max Act: 4.9261. Min Act: -0.1700
Data Index: 1770669 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2073. Min Range: -5.2073
Max Act: 4.9261. Min Act: -0.1700
Data Index: 4949351 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2073. Min Range: -5.2073
Max Act: 4.9261. Min Act: -0.1700
Data Index: 5673545 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2073. Min Range: -5.2073
Max Act: 4.9261. Min Act: -0.1700
Data Index: 1775658 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2073. Min Range: -5.2073
Max Act: 4.9261. Min Act: -0.1700
Data Index: 8660 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2073. Min Range: -5.2073
Max Act: 4.8948. Min Act: -0.1700
Data Index: 339374 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19