Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1627 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.4720. Min Act: -0.1700
Data Index: 4961982 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2220. Min Act: -0.1700
Data Index: 1667632 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2220. Min Act: -0.1700
Data Index: 7241932 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.1907. Min Act: -0.1700
Data Index: 7241929 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.0969. Min Act: -0.1700
Data Index: 3812201 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.0969. Min Act: -0.1700
Data Index: 459866 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.0969. Min Act: -0.1700
Data Index: 945201 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.0657. Min Act: -0.1700
Data Index: 4197468 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.0344. Min Act: -0.1700
Data Index: 2043013 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.0344. Min Act: -0.1700
Data Index: 5931252 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.0344. Min Act: -0.1700
Data Index: 2669234 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.0344. Min Act: -0.1700
Data Index: 5726497 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.0032. Min Act: -0.1700
Data Index: 6016016 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.0032. Min Act: -0.1700
Data Index: 5722941 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4720. Min Range: -4.4720
Max Act: 3.9719. Min Act: -0.1700
Data Index: 5365213 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4720. Min Range: -4.4720
Max Act: 3.9719. Min Act: -0.1700
Data Index: 1310152 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4720. Min Range: -4.4720
Max Act: 3.9563. Min Act: -0.1700
Data Index: 4634135 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4720. Min Range: -4.4720
Max Act: 3.9406. Min Act: -0.1700
Data Index: 7241930 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4720. Min Range: -4.4720
Max Act: 3.9250. Min Act: -0.1700
Data Index: 3012618 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4720. Min Range: -4.4720
Max Act: 3.9406. Min Act: -0.1700
Data Index: 3745586 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19