Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.4449. Min Act: -0.1700
Data Index: 4927581 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.3823. Min Act: -0.1700
Data Index: 5136741 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.3511. Min Act: -0.1700
Data Index: 1908759 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.3511. Min Act: -0.1700
Data Index: 331562 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.3198. Min Act: -0.1700
Data Index: 8256495 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.3198. Min Act: -0.1700
Data Index: 137843 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2886. Min Act: -0.1700
Data Index: 6080425 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.3198. Min Act: -0.1700
Data Index: 7629057 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.3198. Min Act: -0.1700
Data Index: 603741 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2573. Min Act: -0.1700
Data Index: 4778402 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2886. Min Act: -0.1700
Data Index: 944072 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.3198. Min Act: -0.1700
Data Index: 5062740 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2886. Min Act: -0.1700
Data Index: 3193657 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2573. Min Act: -0.1700
Data Index: 4995857 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2573. Min Act: -0.1700
Data Index: 4434096 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2573. Min Act: -0.1700
Data Index: 1192607 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2573. Min Act: -0.1700
Data Index: 5914965 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2261. Min Act: -0.1700
Data Index: 3005903 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2261. Min Act: -0.1700
Data Index: 2305084 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4449. Min Range: -4.4449
Max Act: 4.2261. Min Act: -0.1700
Data Index: 3255234 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19