Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2800. Min Range: -5.2800
Max Act: 5.2800. Min Act: -0.1700
Data Index: 192007 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2800. Min Range: -5.2800
Max Act: 5.2487. Min Act: -0.1700
Data Index: 3315960 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2800. Min Range: -5.2800
Max Act: 5.1862. Min Act: -0.1700
Data Index: 8563954 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2800. Min Range: -5.2800
Max Act: 5.1862. Min Act: -0.1700
Data Index: 3138770 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2800. Min Range: -5.2800
Max Act: 5.1550. Min Act: -0.1700
Data Index: 1534063 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2800. Min Range: -5.2800
Max Act: 5.1237. Min Act: -0.1700
Data Index: 2867662 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2800. Min Range: -5.2800
Max Act: 5.1237. Min Act: -0.1700
Data Index: 4558566 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2800. Min Range: -5.2800
Max Act: 5.0612. Min Act: -0.1700
Data Index: 5472319 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2800. Min Range: -5.2800
Max Act: 5.0612. Min Act: -0.1700
Data Index: 5229912 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2800. Min Range: -5.2800
Max Act: 5.0612. Min Act: -0.1700
Data Index: 4074798 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2800. Min Range: -5.2800
Max Act: 4.9987. Min Act: -0.1700
Data Index: 1142776 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2800. Min Range: -5.2800
Max Act: 4.9987. Min Act: -0.1700
Data Index: 2747918 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2800. Min Range: -5.2800
Max Act: 4.9987. Min Act: -0.1700
Data Index: 2144649 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2800. Min Range: -5.2800
Max Act: 4.9362. Min Act: -0.1700
Data Index: 7347095 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2800. Min Range: -5.2800
Max Act: 4.9050. Min Act: -0.1700
Data Index: 8094395 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2800. Min Range: -5.2800
Max Act: 4.9362. Min Act: -0.1700
Data Index: 4862057 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2800. Min Range: -5.2800
Max Act: 4.9362. Min Act: -0.1700
Data Index: 8437947 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2800. Min Range: -5.2800
Max Act: 4.9362. Min Act: -0.1700
Data Index: 6876179 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2800. Min Range: -5.2800
Max Act: 4.9362. Min Act: -0.1700
Data Index: 4544400 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2800. Min Range: -5.2800
Max Act: 4.9050. Min Act: -0.1700
Data Index: 1685854 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19