Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1733. Min Act: -0.1700
Data Index: 1402318 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1576. Min Act: -0.1700
Data Index: 2691119 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1418. Min Act: -0.1700
Data Index: 1389552 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1418. Min Act: -0.1700
Data Index: 7471768 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1418. Min Act: -0.1700
Data Index: 3480790 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.0946. Min Act: -0.1700
Data Index: 4492533 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1261. Min Act: -0.1700
Data Index: 3044783 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1261. Min Act: -0.1700
Data Index: 2481293 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1261. Min Act: -0.1700
Data Index: 1778000 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1103. Min Act: -0.1700
Data Index: 8223434 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1103. Min Act: -0.1700
Data Index: 7518825 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.0946. Min Act: -0.1700
Data Index: 7542540 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.1103. Min Act: -0.1700
Data Index: 4804716 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.0788. Min Act: -0.1700
Data Index: 5118248 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.0788. Min Act: -0.1700
Data Index: 2299172 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.0788. Min Act: -0.1700
Data Index: 3521932 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.0788. Min Act: -0.1700
Data Index: 3553422 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.0788. Min Act: -0.1700
Data Index: 4004938 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.0946. Min Act: -0.1700
Data Index: 7734516 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1733. Min Range: -3.1733
Max Act: 3.0946. Min Act: -0.1700
Data Index: 1417821 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19