Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4486 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.5479. Min Act: -0.1700
Data Index: 2659632 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.5479. Min Act: -0.1700
Data Index: 2292912 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.5479. Min Act: -0.1700
Data Index: 3892702 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.5479. Min Act: -0.1700
Data Index: 1258379 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.4854. Min Act: -0.1700
Data Index: 3272635 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.4229. Min Act: -0.1700
Data Index: 3670166 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.4229. Min Act: -0.1700
Data Index: 8340664 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.4229. Min Act: -0.1700
Data Index: 1050720 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.3604. Min Act: -0.1700
Data Index: 8388454 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.3604. Min Act: -0.1700
Data Index: 2195049 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.3604. Min Act: -0.1700
Data Index: 4081958 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.3604. Min Act: -0.1700
Data Index: 2404155 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.3604. Min Act: -0.1700
Data Index: 8334102 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.2354. Min Act: -0.1700
Data Index: 7606418 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.2354. Min Act: -0.1700
Data Index: 2592380 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.2979. Min Act: -0.1700
Data Index: 6041675 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.2354. Min Act: -0.1700
Data Index: 1487369 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.2354. Min Act: -0.1700
Data Index: 110001 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.2354. Min Act: -0.1700
Data Index: 4782369 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5479. Min Range: -8.5479
Max Act: 8.2354. Min Act: -0.1700
Data Index: 7166906 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19