Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 58 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0440. Min Act: -0.0002

Data Index: 609112 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0468. Min Act: -0.0002

Data Index: 674169 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1282524 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0410. Min Act: -0.0002

Data Index: 617824 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0407. Min Act: -0.0002

Data Index: 615316 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0481. Min Act: -0.0002

Data Index: 983440 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0412. Min Act: -0.0002

Data Index: 167750 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1134108 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0390. Min Act: -0.0002

Data Index: 10613 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1637769 (Python Code)

Max Activating Token Index: 377

Text #10

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0361. Min Act: -0.0002

Data Index: 75183 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0363. Min Act: -0.0002

Data Index: 5095 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0435. Min Act: -0.0002

Data Index: 181903 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0371. Min Act: -0.0002

Data Index: 903811 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0344. Min Act: -0.0002

Data Index: 798294 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0348. Min Act: -0.0002

Data Index: 888830 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0331. Min Act: -0.0002

Data Index: 342600 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0419. Min Act: -0.0002

Data Index: 701088 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0404. Min Act: -0.0002

Data Index: 496277 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1282668 (C4 (Web Text))

Max Activating Token Index: 51