Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5394 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.9228. Min Act: -0.1700
Data Index: 3804000 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.9540. Min Act: -0.1700
Data Index: 7482980 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.6415. Min Act: -0.1700
Data Index: 7795777 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.6415. Min Act: -0.1700
Data Index: 3718280 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.6415. Min Act: -0.1700
Data Index: 5213455 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.6415. Min Act: -0.1700
Data Index: 6795532 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.6103. Min Act: -0.1700
Data Index: 1179953 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.6103. Min Act: -0.1700
Data Index: 737709 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.6103. Min Act: -0.1700
Data Index: 8799982 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.6103. Min Act: -0.1700
Data Index: 647025 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.6103. Min Act: -0.1700
Data Index: 6109533 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.5790. Min Act: -0.1700
Data Index: 7572766 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.6103. Min Act: -0.1700
Data Index: 4659817 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.5790. Min Act: -0.1700
Data Index: 252855 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.5478. Min Act: -0.1700
Data Index: 2549581 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.5478. Min Act: -0.1700
Data Index: 8763954 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.5478. Min Act: -0.1700
Data Index: 3143454 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.5165. Min Act: -0.1700
Data Index: 8611680 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.5165. Min Act: -0.1700
Data Index: 6000750 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9540. Min Range: -4.9540
Max Act: 4.5165. Min Act: -0.1700
Data Index: 4648508 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19