Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 454 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0632. Min Range: -6.0632
Max Act: 6.0632. Min Act: -0.1700
Data Index: 8725353 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.9695. Min Act: -0.1700
Data Index: 7243940 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.9695. Min Act: -0.1700
Data Index: 8434153 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.9695. Min Act: -0.1700
Data Index: 1030236 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.9382. Min Act: -0.1700
Data Index: 6530405 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.9070. Min Act: -0.1700
Data Index: 1841676 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.9070. Min Act: -0.1700
Data Index: 5582169 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.9070. Min Act: -0.1700
Data Index: 8277603 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8757. Min Act: -0.1700
Data Index: 1712369 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8757. Min Act: -0.1700
Data Index: 4682872 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8757. Min Act: -0.1700
Data Index: 4202875 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8757. Min Act: -0.1700
Data Index: 363709 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8445. Min Act: -0.1700
Data Index: 627001 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8757. Min Act: -0.1700
Data Index: 6933602 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8445. Min Act: -0.1700
Data Index: 6271408 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8445. Min Act: -0.1700
Data Index: 5171219 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8757. Min Act: -0.1700
Data Index: 7432667 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8445. Min Act: -0.1700
Data Index: 333737 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8132. Min Act: -0.1700
Data Index: 1672556 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0632. Min Range: -6.0632
Max Act: 5.8445. Min Act: -0.1700
Data Index: 7920422 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19