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

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

Neuron 4592 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.8997. Min Act: -0.0000

Data Index: 359896 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.8190. Min Act: -0.0000

Data Index: 434154 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.8774. Min Act: -0.0000

Data Index: 104279 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.7965. Min Act: -0.0000

Data Index: 1282188 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.8674. Min Act: -0.0000

Data Index: 1336407 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.7639. Min Act: -0.0000

Data Index: 1358056 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.6397. Min Act: -0.0000

Data Index: 738422 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.7367. Min Act: -0.0000

Data Index: 890830 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.6363. Min Act: -0.0000

Data Index: 672518 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.7208. Min Act: -0.0000

Data Index: 489879 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.7169. Min Act: -0.0000

Data Index: 221727 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.6934. Min Act: -0.0000

Data Index: 749024 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.5718. Min Act: -0.0000

Data Index: 673830 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.6532. Min Act: -0.0000

Data Index: 192816 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.6491. Min Act: -0.0000

Data Index: 1331407 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.6346. Min Act: 0.0000

Data Index: 1312047 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.7106. Min Act: -0.0000

Data Index: 331296 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.7211. Min Act: -0.0000

Data Index: 263898 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.6204. Min Act: -0.0000

Data Index: 1005889 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 1.8997. Min Range: -1.8997

Max Act: 1.6171. Min Act: -0.0000

Data Index: 559258 (C4 (Web Text))

Max Activating Token Index: 610