Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 246 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.7857. Min Act: -0.1700
Data Index: 4800695 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.6607. Min Act: -0.1700
Data Index: 6458116 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.7232. Min Act: -0.1700
Data Index: 1212846 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.5982. Min Act: -0.1700
Data Index: 6578383 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.4732. Min Act: -0.1700
Data Index: 5939150 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.4732. Min Act: -0.1700
Data Index: 8342396 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.2857. Min Act: -0.1700
Data Index: 4999187 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.2545. Min Act: -0.1700
Data Index: 8660392 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.1920. Min Act: -0.1700
Data Index: 2309226 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.1607. Min Act: -0.1700
Data Index: 3250669 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.0670. Min Act: -0.1700
Data Index: 4182423 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.0045. Min Act: -0.1700
Data Index: 8054489 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.0357. Min Act: -0.1700
Data Index: 6247243 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7857. Min Range: -8.7857
Max Act: 8.0045. Min Act: -0.1700
Data Index: 1491820 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7857. Min Range: -8.7857
Max Act: 7.9732. Min Act: -0.1700
Data Index: 6169018 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7857. Min Range: -8.7857
Max Act: 7.9420. Min Act: -0.1700
Data Index: 668910 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7857. Min Range: -8.7857
Max Act: 7.9420. Min Act: -0.1700
Data Index: 5662438 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7857. Min Range: -8.7857
Max Act: 7.8482. Min Act: -0.1700
Data Index: 7000900 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7857. Min Range: -8.7857
Max Act: 7.8170. Min Act: -0.1700
Data Index: 7271427 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7857. Min Range: -8.7857
Max Act: 7.7857. Min Act: -0.1700
Data Index: 2467895 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19