Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.6244. Min Act: -0.1700
Data Index: 7330664 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.4682. Min Act: -0.1700
Data Index: 8589122 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.4369. Min Act: -0.1700
Data Index: 6034842 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.3744. Min Act: -0.1700
Data Index: 184954 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.2494. Min Act: -0.1700
Data Index: 2884432 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.2494. Min Act: -0.1700
Data Index: 5609704 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.2494. Min Act: -0.1700
Data Index: 1024565 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.2494. Min Act: -0.1700
Data Index: 4580374 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.2494. Min Act: -0.1700
Data Index: 6292392 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.2182. Min Act: -0.1700
Data Index: 3965491 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.2182. Min Act: -0.1700
Data Index: 1193773 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.2182. Min Act: -0.1700
Data Index: 4377951 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.1869. Min Act: -0.1700
Data Index: 8379885 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.1244. Min Act: -0.1700
Data Index: 6875698 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.1244. Min Act: -0.1700
Data Index: 5119562 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.1557. Min Act: -0.1700
Data Index: 952676 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.1557. Min Act: -0.1700
Data Index: 431817 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.0932. Min Act: -0.1700
Data Index: 7615668 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.0932. Min Act: -0.1700
Data Index: 89595 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6244. Min Range: -6.6244
Max Act: 6.0619. Min Act: -0.1700
Data Index: 255484 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19