Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.3522. Min Act: -0.1700
Data Index: 374082 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.3209. Min Act: -0.1700
Data Index: 575710 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.2897. Min Act: -0.1700
Data Index: 1895043 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.2272. Min Act: -0.1700
Data Index: 7863313 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.2272. Min Act: -0.1700
Data Index: 5987952 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.1647. Min Act: -0.1700
Data Index: 6577848 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.1647. Min Act: -0.1700
Data Index: 373326 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.1334. Min Act: -0.1700
Data Index: 2812795 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.1647. Min Act: -0.1700
Data Index: 7977524 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.1334. Min Act: -0.1700
Data Index: 1776896 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.1022. Min Act: -0.1700
Data Index: 7276573 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.1022. Min Act: -0.1700
Data Index: 5760180 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.0709. Min Act: -0.1700
Data Index: 4539651 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.0709. Min Act: -0.1700
Data Index: 5830831 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.0709. Min Act: -0.1700
Data Index: 5615423 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.0709. Min Act: -0.1700
Data Index: 8286470 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.0709. Min Act: -0.1700
Data Index: 2115601 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.0396. Min Act: -0.1700
Data Index: 6555655 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.0396. Min Act: -0.1700
Data Index: 1951386 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3522. Min Range: -4.3522
Max Act: 4.0396. Min Act: -0.1700
Data Index: 2277810 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19