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

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

Neuron 346 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.3809. Min Act: -0.0000

Data Index: 11516 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0895. Min Act: -0.0000

Data Index: 274355 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1881. Min Act: -0.0000

Data Index: 847328 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0919. Min Act: -0.0000

Data Index: 465178 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0844. Min Act: -0.0000

Data Index: 744599 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1755. Min Act: -0.0000

Data Index: 183756 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1315. Min Act: -0.0000

Data Index: 592086 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1029519 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1058. Min Act: -0.0000

Data Index: 419105 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9688. Min Act: -0.0000

Data Index: 340895 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9997. Min Act: -0.0000

Data Index: 194056 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0137. Min Act: -0.0000

Data Index: 627055 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0361. Min Act: -0.0000

Data Index: 227154 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9421. Min Act: -0.0000

Data Index: 541003 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9706. Min Act: -0.0000

Data Index: 769474 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9457. Min Act: -0.0000

Data Index: 745893 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1044621 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9283. Min Act: -0.0000

Data Index: 35781 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9507. Min Act: -0.0000

Data Index: 258565 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9144. Min Act: -0.0000

Data Index: 471096 (C4 (Web Text))

Max Activating Token Index: 11