Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 668 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.7575. Min Act: -0.0000

Data Index: 966587 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.8448. Min Act: -0.0000

Data Index: 130538 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.5715. Min Act: -0.0000

Data Index: 607126 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.7267. Min Act: -0.0000

Data Index: 164445 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.5414. Min Act: -0.0000

Data Index: 567022 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.4624. Min Act: -0.0000

Data Index: 555093 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.6172. Min Act: -0.0000

Data Index: 1193545 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.5758. Min Act: -0.0000

Data Index: 453265 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.7162. Min Act: -0.0000

Data Index: 1047849 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.5213. Min Act: -0.0000

Data Index: 1096631 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.3428. Min Act: -0.0000

Data Index: 1015111 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.5009. Min Act: -0.0000

Data Index: 386918 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.6358. Min Act: -0.0000

Data Index: 1050670 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.4021. Min Act: -0.0000

Data Index: 832275 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.5672. Min Act: -0.0000

Data Index: 1089729 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.3749. Min Act: -0.0000

Data Index: 606250 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.3642. Min Act: -0.0000

Data Index: 745808 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.3406. Min Act: -0.0000

Data Index: 205723 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.2780. Min Act: -0.0000

Data Index: 1357916 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 4.8448. Min Range: -4.8448

Max Act: 4.2926. Min Act: -0.0000

Data Index: 1284057 (C4 (Web Text))

Max Activating Token Index: 710