Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2005. Min Range: -7.2005
Max Act: 7.2005. Min Act: -0.1700
Data Index: 2087820 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.7005. Min Act: -0.1700
Data Index: 3179496 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.6693. Min Act: -0.1700
Data Index: 5566655 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.6380. Min Act: -0.1700
Data Index: 7217677 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.5755. Min Act: -0.1700
Data Index: 5886306 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.5130. Min Act: -0.1700
Data Index: 1429734 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.4818. Min Act: -0.1700
Data Index: 1794652 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.4193. Min Act: -0.1700
Data Index: 216985 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.3880. Min Act: -0.1700
Data Index: 6583592 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.3880. Min Act: -0.1700
Data Index: 3017936 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.3568. Min Act: -0.1700
Data Index: 7809327 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.3568. Min Act: -0.1700
Data Index: 8515979 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.3255. Min Act: -0.1700
Data Index: 75203 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.2630. Min Act: -0.1700
Data Index: 2491456 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.2630. Min Act: -0.1700
Data Index: 8293290 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.2630. Min Act: -0.1700
Data Index: 7239650 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.2318. Min Act: -0.1700
Data Index: 1973523 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.2318. Min Act: -0.1700
Data Index: 5150111 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.2318. Min Act: -0.1700
Data Index: 7988146 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2005. Min Range: -7.2005
Max Act: 6.2005. Min Act: -0.1700
Data Index: 2819378 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19