Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4032 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.3523. Min Range: -3.3523
Max Act: 3.3523. Min Act: -0.0001
Data Index: 251262 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3523. Min Range: -3.3523
Max Act: 2.3622. Min Act: -0.0001
Data Index: 640312 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3523. Min Range: -3.3523
Max Act: 2.2796. Min Act: -0.0001
Data Index: 736016 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3523. Min Range: -3.3523
Max Act: 2.1247. Min Act: -0.0001
Data Index: 335764 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.9159. Min Act: -0.0001
Data Index: 573344 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.9947. Min Act: -0.0001
Data Index: 554306 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3523. Min Range: -3.3523
Max Act: 2.3368. Min Act: -0.0001
Data Index: 517220 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.7228. Min Act: -0.0001
Data Index: 716053 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.7703. Min Act: -0.0001
Data Index: 715847 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.5308. Min Act: -0.0001
Data Index: 1026457 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.6061. Min Act: -0.0001
Data Index: 562772 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.3461. Min Act: -0.0001
Data Index: 300610 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.4572. Min Act: -0.0001
Data Index: 600710 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.4509. Min Act: -0.0001
Data Index: 926736 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.4757. Min Act: -0.0001
Data Index: 382112 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.4736. Min Act: -0.0001
Data Index: 624494 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.4325. Min Act: -0.0001
Data Index: 924619 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.4126. Min Act: -0.0001
Data Index: 103115 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.3324. Min Act: -0.0001
Data Index: 560443 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3523. Min Range: -3.3523
Max Act: 1.3542. Min Act: -0.0001
Data Index: 498083 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19