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

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

Neuron 1499 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: 0.9548. Min Range: -0.9548

Max Act: 0.9548. Min Act: -0.0001

Data Index: 1461450 (Python Code)

Max Activating Token Index: 980

Text #1

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.8414. Min Act: -0.0001

Data Index: 200054 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7609. Min Act: -0.0001

Data Index: 1156845 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6824. Min Act: -0.0002

Data Index: 601321 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6967. Min Act: -0.0001

Data Index: 1349330 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6888. Min Act: -0.0001

Data Index: 698973 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7003. Min Act: -0.0002

Data Index: 441091 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7420. Min Act: -0.0002

Data Index: 1151424 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6419. Min Act: -0.0001

Data Index: 113043 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6199. Min Act: -0.0001

Data Index: 1118411 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6402. Min Act: -0.0002

Data Index: 293918 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6992. Min Act: -0.0001

Data Index: 300796 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7018. Min Act: -0.0002

Data Index: 325669 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6249. Min Act: -0.0002

Data Index: 990822 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6160. Min Act: -0.0001

Data Index: 1240441 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.5904. Min Act: -0.0002

Data Index: 248244 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6265. Min Act: -0.0001

Data Index: 333587 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1218044 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6239. Min Act: -0.0001

Data Index: 670165 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6980. Min Act: -0.0002

Data Index: 354770 (C4 (Web Text))

Max Activating Token Index: 305