Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.5667. Min Act: -0.1700
Data Index: 7541713 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.5042. Min Act: -0.1700
Data Index: 2461419 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.4729. Min Act: -0.1700
Data Index: 4572398 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.5042. Min Act: -0.1700
Data Index: 4158329 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.4417. Min Act: -0.1700
Data Index: 2798012 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.3479. Min Act: -0.1700
Data Index: 2410343 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.3479. Min Act: -0.1700
Data Index: 8086421 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.3792. Min Act: -0.1700
Data Index: 5937208 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.3479. Min Act: -0.1700
Data Index: 1434480 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.3167. Min Act: -0.1700
Data Index: 5457983 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.3479. Min Act: -0.1700
Data Index: 8101224 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.3167. Min Act: -0.1700
Data Index: 7656997 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.3167. Min Act: -0.1700
Data Index: 1873807 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.2854. Min Act: -0.1700
Data Index: 7209347 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.2854. Min Act: -0.1700
Data Index: 5627663 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.2542. Min Act: -0.1700
Data Index: 4274560 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.2542. Min Act: -0.1700
Data Index: 7656998 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.2542. Min Act: -0.1700
Data Index: 7468025 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.2542. Min Act: -0.1700
Data Index: 3927286 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5667. Min Range: -7.5667
Max Act: 7.2229. Min Act: -0.1700
Data Index: 77809 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19