Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2902 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.7818. Min Act: -0.1700
Data Index: 4751128 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.6723. Min Act: -0.1700
Data Index: 2057384 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.6254. Min Act: -0.1700
Data Index: 3215153 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.6254. Min Act: -0.1700
Data Index: 6392231 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.5628. Min Act: -0.1700
Data Index: 4821995 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.5315. Min Act: -0.1700
Data Index: 649589 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.5002. Min Act: -0.1700
Data Index: 8454978 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.4845. Min Act: -0.1700
Data Index: 2507307 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.5002. Min Act: -0.1700
Data Index: 3458300 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.4688. Min Act: -0.1700
Data Index: 3988335 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.4532. Min Act: -0.1700
Data Index: 1200377 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.4532. Min Act: -0.1700
Data Index: 8250749 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.4218. Min Act: -0.1700
Data Index: 7925086 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.4375. Min Act: -0.1700
Data Index: 8789546 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.4218. Min Act: -0.1700
Data Index: 3144819 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.4061. Min Act: -0.1700
Data Index: 8238970 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.3905. Min Act: -0.1700
Data Index: 2149258 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.4061. Min Act: -0.1700
Data Index: 7401064 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.3905. Min Act: -0.1700
Data Index: 5945496 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7818. Min Range: -3.7818
Max Act: 3.3748. Min Act: -0.1700
Data Index: 8447766 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19