Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1317 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 1.4490. Min Range: -1.4490

Max Act: 1.1260. Min Act: -0.0003

Data Index: 855427 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 1.4490. Min Range: -1.4490

Max Act: 1.4490. Min Act: -0.0003

Data Index: 758853 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.4490. Min Range: -1.4490

Max Act: 1.0754. Min Act: -0.0003

Data Index: 295318 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 1.4490. Min Range: -1.4490

Max Act: 1.1111. Min Act: -0.0003

Data Index: 794852 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.4490. Min Range: -1.4490

Max Act: 1.1489. Min Act: -0.0003

Data Index: 417776 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 1.4490. Min Range: -1.4490

Max Act: 1.0588. Min Act: -0.0003

Data Index: 212517 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 1.4490. Min Range: -1.4490

Max Act: 1.0573. Min Act: -0.0003

Data Index: 1210110 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 1.4490. Min Range: -1.4490

Max Act: 1.0325. Min Act: -0.0003

Data Index: 579726 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.9872. Min Act: -0.0003

Data Index: 781219 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.9590. Min Act: -0.0003

Data Index: 526649 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.8565. Min Act: -0.0003

Data Index: 874284 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.8917. Min Act: -0.0004

Data Index: 601452 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.8683. Min Act: -0.0003

Data Index: 1112426 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.8359. Min Act: -0.0003

Data Index: 1145720 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.9159. Min Act: -0.0003

Data Index: 1317087 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.8621. Min Act: -0.0003

Data Index: 449568 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.8298. Min Act: -0.0003

Data Index: 228188 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.8128. Min Act: -0.0003

Data Index: 124211 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.8888. Min Act: -0.0003

Data Index: 1252184 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 1.4490. Min Range: -1.4490

Max Act: 0.8544. Min Act: -0.0003

Data Index: 639613 (C4 (Web Text))

Max Activating Token Index: 80