Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3169 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0002

Data Index: 708391 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0375. Min Act: -0.0003

Data Index: 216305 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0361. Min Act: -0.0003

Data Index: 756783 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0358. Min Act: -0.0003

Data Index: 527742 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0349. Min Act: -0.0002

Data Index: 256124 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0348. Min Act: -0.0003

Data Index: 145975 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1107271 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0336. Min Act: -0.0003

Data Index: 345886 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0314. Min Act: -0.0003

Data Index: 419900 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0314. Min Act: -0.0003

Data Index: 55635 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0314. Min Act: -0.0003

Data Index: 49377 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0314. Min Act: -0.0003

Data Index: 455018 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0314. Min Act: -0.0003

Data Index: 840366 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1322416 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1200400 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1202486 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1097442 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1298862 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1252430 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0308. Min Act: -0.0003

Data Index: 292690 (C4 (Web Text))

Max Activating Token Index: 11