Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1465 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.3561. Min Act: -0.1700
Data Index: 1652271 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.3248. Min Act: -0.1700
Data Index: 4346911 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.2311. Min Act: -0.1700
Data Index: 2941636 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.2311. Min Act: -0.1700
Data Index: 4539545 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.2311. Min Act: -0.1700
Data Index: 344808 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1998. Min Act: -0.1700
Data Index: 1487573 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.0748. Min Act: -0.1700
Data Index: 344813 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.9498. Min Act: -0.1700
Data Index: 4346920 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.9498. Min Act: -0.1700
Data Index: 1487566 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.9186. Min Act: -0.1700
Data Index: 4442278 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8248. Min Act: -0.1700
Data Index: 1487568 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8248. Min Act: -0.1700
Data Index: 5141424 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.7623. Min Act: -0.1700
Data Index: 4468964 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.7311. Min Act: -0.1700
Data Index: 5048368 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.7311. Min Act: -0.1700
Data Index: 8060258 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.7311. Min Act: -0.1700
Data Index: 537458 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.6686. Min Act: -0.1700
Data Index: 2052417 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.6686. Min Act: -0.1700
Data Index: 3990057 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.6686. Min Act: -0.1700
Data Index: 8171656 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.6061. Min Act: -0.1700
Data Index: 6053121 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19