Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.7956. Min Act: -0.1700
Data Index: 6006968 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.7331. Min Act: -0.1700
Data Index: 6048417 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.7331. Min Act: -0.1700
Data Index: 893693 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.6706. Min Act: -0.1700
Data Index: 8413416 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.4831. Min Act: -0.1700
Data Index: 4889784 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.4206. Min Act: -0.1700
Data Index: 7983402 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.3581. Min Act: -0.1700
Data Index: 2181525 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.3581. Min Act: -0.1700
Data Index: 2816270 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.2331. Min Act: -0.1700
Data Index: 3830107 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.1706. Min Act: -0.1700
Data Index: 2415274 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.1706. Min Act: -0.1700
Data Index: 4558405 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.1081. Min Act: -0.1700
Data Index: 674562 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.0456. Min Act: -0.1700
Data Index: 3378543 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.1081. Min Act: -0.1700
Data Index: 7049613 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.0456. Min Act: -0.1700
Data Index: 5614786 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7956. Min Range: -8.7956
Max Act: 8.0456. Min Act: -0.1700
Data Index: 5135223 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7956. Min Range: -8.7956
Max Act: 7.9831. Min Act: -0.1700
Data Index: 1957968 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7956. Min Range: -8.7956
Max Act: 7.9831. Min Act: -0.1700
Data Index: 4529629 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7956. Min Range: -8.7956
Max Act: 7.9831. Min Act: -0.1700
Data Index: 5877661 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7956. Min Range: -8.7956
Max Act: 7.9831. Min Act: -0.1700
Data Index: 1593151 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19