Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5110 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.0582. Min Range: -10.0582
Max Act: 10.0582. Min Act: -0.1700
Data Index: 8681905 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.4957. Min Act: -0.1700
Data Index: 3872840 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.3707. Min Act: -0.1700
Data Index: 6814662 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.2457. Min Act: -0.1700
Data Index: 6110804 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.2457. Min Act: -0.1700
Data Index: 415592 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.1207. Min Act: -0.1700
Data Index: 8136508 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.1832. Min Act: -0.1700
Data Index: 7692861 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.1207. Min Act: -0.1700
Data Index: 2562778 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.1207. Min Act: -0.1700
Data Index: 5068464 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.1207. Min Act: -0.1700
Data Index: 7725664 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.1207. Min Act: -0.1700
Data Index: 7241288 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.0582. Min Act: -0.1700
Data Index: 6247356 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.0582. Min Act: -0.1700
Data Index: 6462862 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.0582. Min Act: -0.1700
Data Index: 6496133 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0582. Min Range: -10.0582
Max Act: 9.0582. Min Act: -0.1700
Data Index: 5292090 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0582. Min Range: -10.0582
Max Act: 8.9957. Min Act: -0.1700
Data Index: 1018895 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0582. Min Range: -10.0582
Max Act: 8.9957. Min Act: -0.1700
Data Index: 6015322 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0582. Min Range: -10.0582
Max Act: 8.9332. Min Act: -0.1700
Data Index: 7972729 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0582. Min Range: -10.0582
Max Act: 8.9957. Min Act: -0.1700
Data Index: 2663503 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0582. Min Range: -10.0582
Max Act: 8.9332. Min Act: -0.1700
Data Index: 541259 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19