Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.6697. Min Act: -0.1700
Data Index: 123020 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.6384. Min Act: -0.1700
Data Index: 5157324 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.6072. Min Act: -0.1700
Data Index: 3440027 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.5134. Min Act: -0.1700
Data Index: 3679041 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.5759. Min Act: -0.1700
Data Index: 5993753 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.5134. Min Act: -0.1700
Data Index: 339647 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.4822. Min Act: -0.1700
Data Index: 2018198 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.4822. Min Act: -0.1700
Data Index: 7772860 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.4197. Min Act: -0.1700
Data Index: 2790533 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.4197. Min Act: -0.1700
Data Index: 6805281 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.3884. Min Act: -0.1700
Data Index: 7464987 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.4197. Min Act: -0.1700
Data Index: 2558203 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.3572. Min Act: -0.1700
Data Index: 2904357 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.3572. Min Act: -0.1700
Data Index: 3897677 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.3572. Min Act: -0.1700
Data Index: 2531893 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.3259. Min Act: -0.1700
Data Index: 1452375 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.3572. Min Act: -0.1700
Data Index: 812626 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.3572. Min Act: -0.1700
Data Index: 1452377 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.2947. Min Act: -0.1700
Data Index: 7772861 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6697. Min Range: -6.6697
Max Act: 6.3259. Min Act: -0.1700
Data Index: 3679036 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19