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

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

Neuron 409 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.7722. Min Act: -0.0002

Data Index: 333276 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.8660. Min Act: -0.0002

Data Index: 1252671 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.7743. Min Act: -0.0002

Data Index: 430820 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.7418. Min Act: -0.0002

Data Index: 1117096 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6206. Min Act: -0.0002

Data Index: 1246110 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6727. Min Act: -0.0002

Data Index: 512634 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6355. Min Act: -0.0002

Data Index: 1068366 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6454. Min Act: -0.0002

Data Index: 552024 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6525. Min Act: -0.0002

Data Index: 884462 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6525. Min Act: -0.0002

Data Index: 1242258 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6539. Min Act: -0.0002

Data Index: 1268901 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6607. Min Act: -0.0002

Data Index: 1040102 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5572. Min Act: -0.0002

Data Index: 727889 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6628. Min Act: -0.0002

Data Index: 549574 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6349. Min Act: -0.0002

Data Index: 917384 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6377. Min Act: -0.0002

Data Index: 151942 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6148. Min Act: -0.0002

Data Index: 1028243 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5825. Min Act: -0.0002

Data Index: 731916 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5647. Min Act: -0.0002

Data Index: 661800 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6139. Min Act: -0.0002

Data Index: 362061 (C4 (Web Text))

Max Activating Token Index: 308