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

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

Neuron 5869 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: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0002

Data Index: 242598 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0396. Min Act: -0.0002

Data Index: 814967 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1569646 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1498603 (Python Code)

Max Activating Token Index: 678

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1595484 (Python Code)

Max Activating Token Index: 648

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0357. Min Act: -0.0002

Data Index: 569956 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0360. Min Act: -0.0002

Data Index: 320059 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0359. Min Act: -0.0002

Data Index: 313036 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1579725 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1613995 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0336. Min Act: -0.0002

Data Index: 385177 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0334. Min Act: -0.0002

Data Index: 331169 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1154782 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0322. Min Act: -0.0002

Data Index: 868916 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1228978 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1099107 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1493439 (Python Code)

Max Activating Token Index: 804

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1365713 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1115934 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0320. Min Act: -0.0002

Data Index: 869841 (C4 (Web Text))

Max Activating Token Index: 378