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

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

Neuron 1596 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1332996 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1407965 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0374. Min Act: -0.0002

Data Index: 187697 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1655245 (Python Code)

Max Activating Token Index: 58

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1454093 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1593802 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1535324 (Python Code)

Max Activating Token Index: 405

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1402502 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1480183 (Python Code)

Max Activating Token Index: 44

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1385958 (Python Code)

Max Activating Token Index: 520

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1604161 (Python Code)

Max Activating Token Index: 192

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1332759 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1442417 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1323457 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1443344 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1652172 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0297. Min Act: -0.0002

Data Index: 651848 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1172279 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1003373 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1200958 (C4 (Web Text))

Max Activating Token Index: 1