Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3452 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6969. Min Range: -8.6969
Max Act: 8.6969. Min Act: -0.1700
Data Index: 1496240 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6969. Min Range: -8.6969
Max Act: 8.0094. Min Act: -0.1700
Data Index: 8382042 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.6656. Min Act: -0.1700
Data Index: 6181129 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.5406. Min Act: -0.1700
Data Index: 4116503 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.4781. Min Act: -0.1700
Data Index: 1591223 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.4469. Min Act: -0.1700
Data Index: 3649997 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.4469. Min Act: -0.1700
Data Index: 940542 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.4156. Min Act: -0.1700
Data Index: 602623 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.4156. Min Act: -0.1700
Data Index: 4673976 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.4156. Min Act: -0.1700
Data Index: 4822041 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.3531. Min Act: -0.1700
Data Index: 1252631 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.3844. Min Act: -0.1700
Data Index: 1537176 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.3219. Min Act: -0.1700
Data Index: 1546985 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.3531. Min Act: -0.1700
Data Index: 5784694 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.3219. Min Act: -0.1700
Data Index: 8810630 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.2906. Min Act: -0.1700
Data Index: 5334519 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.3219. Min Act: -0.1700
Data Index: 5407185 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.3531. Min Act: -0.1700
Data Index: 2705649 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.3219. Min Act: -0.1700
Data Index: 2480965 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6969. Min Range: -8.6969
Max Act: 7.3219. Min Act: -0.1700
Data Index: 6523536 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19