Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.8960. Min Act: -0.1700
Data Index: 3486764 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.8790. Min Act: -0.1700
Data Index: 3686265 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.8619. Min Act: -0.1700
Data Index: 94145 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.8447. Min Act: -0.1700
Data Index: 5990923 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.8276. Min Act: -0.1700
Data Index: 4017170 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.8104. Min Act: -0.1700
Data Index: 1224013 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.8104. Min Act: -0.1700
Data Index: 5165176 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.8104. Min Act: -0.1700
Data Index: 8546327 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7932. Min Act: -0.1700
Data Index: 8785682 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7932. Min Act: -0.1700
Data Index: 7445334 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7760. Min Act: -0.1700
Data Index: 5256013 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7760. Min Act: -0.1700
Data Index: 5482072 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7760. Min Act: -0.1700
Data Index: 1908220 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7587. Min Act: -0.1700
Data Index: 4427842 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7587. Min Act: -0.1700
Data Index: 712868 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7587. Min Act: -0.1700
Data Index: 8079271 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7415. Min Act: -0.1700
Data Index: 5075905 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7242. Min Act: -0.1700
Data Index: 4903151 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7242. Min Act: -0.1700
Data Index: 599204 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8960. Min Range: -1.8960
Max Act: 1.7242. Min Act: -0.1700
Data Index: 2137692 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19