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

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

Neuron 3591 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.3910. Min Act: -0.0001

Data Index: 1105563 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.2793. Min Act: -0.0001

Data Index: 1295910 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.2041. Min Act: -0.0001

Data Index: 463138 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.0995. Min Act: -0.0001

Data Index: 262274 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.2351. Min Act: -0.0001

Data Index: 806342 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.3073. Min Act: -0.0001

Data Index: 1335635 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.2056. Min Act: -0.0001

Data Index: 1224755 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.1693. Min Act: -0.0001

Data Index: 616970 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.1902. Min Act: -0.0001

Data Index: 15504 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.2277. Min Act: -0.0001

Data Index: 865448 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.1950. Min Act: -0.0001

Data Index: 1339330 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.1207. Min Act: -0.0001

Data Index: 1088804 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.1787. Min Act: -0.0001

Data Index: 745062 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.2585. Min Act: -0.0001

Data Index: 546694 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.1149. Min Act: -0.0001

Data Index: 689560 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.1124. Min Act: -0.0001

Data Index: 824041 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.1388. Min Act: -0.0001

Data Index: 309616 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.0998. Min Act: -0.0001

Data Index: 912019 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.1571. Min Act: -0.0001

Data Index: 87310 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 1.3910. Min Range: -1.3910

Max Act: 1.1302. Min Act: -0.0001

Data Index: 1323266 (C4 (Web Text))

Max Activating Token Index: 259