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

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

Neuron 64 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.8395. Min Act: -0.0002

Data Index: 369261 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.4982. Min Act: -0.0001

Data Index: 313700 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.5334. Min Act: -0.0002

Data Index: 758376 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.4461. Min Act: -0.0001

Data Index: 24824 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.4923. Min Act: -0.0002

Data Index: 528134 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.3841. Min Act: -0.0002

Data Index: 560924 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.3910. Min Act: -0.0001

Data Index: 1598502 (Python Code)

Max Activating Token Index: 1020

Text #7

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.3720. Min Act: -0.0002

Data Index: 183590 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.3719. Min Act: -0.0002

Data Index: 394796 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.2991. Min Act: -0.0001

Data Index: 1577365 (Python Code)

Max Activating Token Index: 320

Text #10

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.3306. Min Act: -0.0002

Data Index: 782736 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.2932. Min Act: -0.0001

Data Index: 11630 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.3293. Min Act: -0.0002

Data Index: 673638 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.2754. Min Act: -0.0001

Data Index: 1328542 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.3316. Min Act: -0.0002

Data Index: 433403 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.2595. Min Act: -0.0002

Data Index: 904562 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.2368. Min Act: -0.0001

Data Index: 160070 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.2409. Min Act: -0.0002

Data Index: 1224160 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.3227. Min Act: -0.0002

Data Index: 460585 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 1.8395. Min Range: -1.8395

Max Act: 1.2709. Min Act: -0.0002

Data Index: 1300507 (C4 (Web Text))

Max Activating Token Index: 1018