Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 915 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2053. Min Range: -6.2053
Max Act: 6.2053. Min Act: -0.1700
Data Index: 2167337 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.8303. Min Act: -0.1700
Data Index: 5936469 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.7053. Min Act: -0.1700
Data Index: 5635189 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.6116. Min Act: -0.1700
Data Index: 6250 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.6116. Min Act: -0.1700
Data Index: 2551050 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.6116. Min Act: -0.1700
Data Index: 8131785 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.6116. Min Act: -0.1700
Data Index: 3014873 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.5491. Min Act: -0.1700
Data Index: 5471624 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.5491. Min Act: -0.1700
Data Index: 1617104 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.5491. Min Act: -0.1700
Data Index: 7900644 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.5178. Min Act: -0.1700
Data Index: 6920334 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.4866. Min Act: -0.1700
Data Index: 478808 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.5178. Min Act: -0.1700
Data Index: 4972313 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.5178. Min Act: -0.1700
Data Index: 7617435 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.5178. Min Act: -0.1700
Data Index: 6630517 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.5178. Min Act: -0.1700
Data Index: 1940571 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.5178. Min Act: -0.1700
Data Index: 2425566 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.4553. Min Act: -0.1700
Data Index: 5759341 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.4866. Min Act: -0.1700
Data Index: 7184440 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2053. Min Range: -6.2053
Max Act: 5.4866. Min Act: -0.1700
Data Index: 3190721 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19