Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4183 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.3853. Min Act: -0.0000

Data Index: 24063 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.3322. Min Act: -0.0000

Data Index: 710661 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2773. Min Act: -0.0000

Data Index: 208312 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2828. Min Act: -0.0000

Data Index: 314918 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2638. Min Act: -0.0000

Data Index: 436101 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1098054 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2532. Min Act: -0.0000

Data Index: 357207 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1320870 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2690. Min Act: -0.0000

Data Index: 477060 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2669. Min Act: -0.0000

Data Index: 20827 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2604. Min Act: -0.0000

Data Index: 137365 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1081127 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1099751 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2450. Min Act: -0.0000

Data Index: 62599 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2504. Min Act: -0.0000

Data Index: 442820 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1343807 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2557. Min Act: -0.0000

Data Index: 976618 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1357283 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2344. Min Act: -0.0000

Data Index: 218231 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2431. Min Act: -0.0000

Data Index: 567750 (C4 (Web Text))

Max Activating Token Index: 460