Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.2766. Min Act: -0.1700
Data Index: 2844917 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.2766. Min Act: -0.1700
Data Index: 4117272 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.2766. Min Act: -0.1700
Data Index: 6494359 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.2601. Min Act: -0.1700
Data Index: 4117268 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.2436. Min Act: -0.1700
Data Index: 7384647 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.2270. Min Act: -0.1700
Data Index: 5018467 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.2270. Min Act: -0.1700
Data Index: 6856840 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.2270. Min Act: -0.1700
Data Index: 5693496 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1939. Min Act: -0.1700
Data Index: 6928550 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.2104. Min Act: -0.1700
Data Index: 5689282 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1772. Min Act: -0.1700
Data Index: 3789678 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1772. Min Act: -0.1700
Data Index: 8314353 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1939. Min Act: -0.1700
Data Index: 8436239 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1772. Min Act: -0.1700
Data Index: 8187855 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1939. Min Act: -0.1700
Data Index: 3085735 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1772. Min Act: -0.1700
Data Index: 6040886 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1772. Min Act: -0.1700
Data Index: 5643572 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1606. Min Act: -0.1700
Data Index: 1967389 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1939. Min Act: -0.1700
Data Index: 1298365 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2766. Min Range: -2.2766
Max Act: 2.1606. Min Act: -0.1700
Data Index: 5417255 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19