Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4602 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0562. Min Range: -2.0562

Max Act: 2.0562. Min Act: -0.0000

Data Index: 890575 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.6866. Min Act: -0.0000

Data Index: 872976 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.4425. Min Act: -0.0000

Data Index: 1092125 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.4700. Min Act: -0.0000

Data Index: 55234 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.4394. Min Act: -0.0000

Data Index: 1326586 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.3800. Min Act: -0.0000

Data Index: 335084 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.4709. Min Act: -0.0000

Data Index: 745448 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.3936. Min Act: -0.0000

Data Index: 17163 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.3775. Min Act: -0.0000

Data Index: 1030698 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.3693. Min Act: -0.0000

Data Index: 19147 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1251922 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.3731. Min Act: -0.0000

Data Index: 1289430 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.3016. Min Act: -0.0000

Data Index: 289085 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.2645. Min Act: -0.0000

Data Index: 979104 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.2175. Min Act: -0.0000

Data Index: 511681 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.2798. Min Act: -0.0000

Data Index: 799747 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.2790. Min Act: -0.0000

Data Index: 334929 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.2539. Min Act: -0.0000

Data Index: 252825 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.2115. Min Act: -0.0000

Data Index: 62130 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 2.0562. Min Range: -2.0562

Max Act: 1.2348. Min Act: -0.0000

Data Index: 491053 (C4 (Web Text))

Max Activating Token Index: 419