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

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

Neuron 3940 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0002

Data Index: 352841 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1214194 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0353. Min Act: -0.0002

Data Index: 600354 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1150885 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0358. Min Act: -0.0002

Data Index: 655901 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0345. Min Act: -0.0002

Data Index: 914397 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0319. Min Act: -0.0002

Data Index: 422367 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0317. Min Act: -0.0002

Data Index: 546699 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0303. Min Act: -0.0002

Data Index: 936560 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0299. Min Act: -0.0002

Data Index: 644654 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0295. Min Act: -0.0002

Data Index: 569109 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0300. Min Act: -0.0002

Data Index: 289655 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0294. Min Act: -0.0002

Data Index: 350651 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1042803 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0285. Min Act: -0.0002

Data Index: 613358 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0278. Min Act: -0.0002

Data Index: 86919 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0279. Min Act: -0.0002

Data Index: 646000 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0278. Min Act: -0.0002

Data Index: 328325 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0281. Min Act: -0.0002

Data Index: 627530 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0271. Min Act: -0.0002

Data Index: 68128 (C4 (Web Text))

Max Activating Token Index: 489