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

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

Neuron 87 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: 0.3272. Min Range: -0.3272

Max Act: 0.3205. Min Act: -0.0003

Data Index: 178124 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.3272. Min Act: -0.0003

Data Index: 451285 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2984. Min Act: -0.0003

Data Index: 817557 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2588. Min Act: -0.0003

Data Index: 1095886 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2829. Min Act: -0.0003

Data Index: 1004502 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2567. Min Act: -0.0003

Data Index: 842577 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2589. Min Act: -0.0004

Data Index: 1342761 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2613. Min Act: -0.0003

Data Index: 564756 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2504. Min Act: -0.0003

Data Index: 1268043 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2340. Min Act: -0.0003

Data Index: 1241421 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2429. Min Act: -0.0003

Data Index: 295724 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2502. Min Act: -0.0004

Data Index: 951783 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2499. Min Act: -0.0003

Data Index: 1185191 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2157. Min Act: -0.0003

Data Index: 252225 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2212. Min Act: -0.0003

Data Index: 1052577 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2336. Min Act: -0.0003

Data Index: 1354830 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2251. Min Act: -0.0003

Data Index: 513427 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2401. Min Act: -0.0003

Data Index: 1006773 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2429. Min Act: -0.0003

Data Index: 9228 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2292. Min Act: -0.0003

Data Index: 633501 (C4 (Web Text))

Max Activating Token Index: 600