Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.5591. Min Act: -0.1700
Data Index: 6149039 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.3716. Min Act: -0.1700
Data Index: 6723415 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.3716. Min Act: -0.1700
Data Index: 4803510 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.3716. Min Act: -0.1700
Data Index: 2834067 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.3404. Min Act: -0.1700
Data Index: 4551284 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.2779. Min Act: -0.1700
Data Index: 793698 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.2466. Min Act: -0.1700
Data Index: 3677378 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.2779. Min Act: -0.1700
Data Index: 3666667 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.2154. Min Act: -0.1700
Data Index: 8216319 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.1529. Min Act: -0.1700
Data Index: 2815122 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.0904. Min Act: -0.1700
Data Index: 8127850 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.0279. Min Act: -0.1700
Data Index: 3213679 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.0279. Min Act: -0.1700
Data Index: 4378924 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5591. Min Range: -8.5591
Max Act: 8.0279. Min Act: -0.1700
Data Index: 5288678 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5591. Min Range: -8.5591
Max Act: 7.9654. Min Act: -0.1700
Data Index: 5244899 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5591. Min Range: -8.5591
Max Act: 7.9341. Min Act: -0.1700
Data Index: 1104491 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5591. Min Range: -8.5591
Max Act: 7.9654. Min Act: -0.1700
Data Index: 7679731 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5591. Min Range: -8.5591
Max Act: 7.9654. Min Act: -0.1700
Data Index: 8227509 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5591. Min Range: -8.5591
Max Act: 7.9341. Min Act: -0.1700
Data Index: 1628044 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5591. Min Range: -8.5591
Max Act: 7.9341. Min Act: -0.1700
Data Index: 6387099 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19