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

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

Neuron 2824 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.2620. Min Act: -0.0000

Data Index: 9033 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.2901. Min Act: -0.0000

Data Index: 283993 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.1832. Min Act: -0.0000

Data Index: 551282 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.1356. Min Act: -0.0000

Data Index: 1250756 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0952. Min Act: -0.0000

Data Index: 1090775 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0487. Min Act: -0.0000

Data Index: 1133422 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1599584 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9382. Min Act: -0.0000

Data Index: 963258 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.8624. Min Act: -0.0000

Data Index: 761821 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.8429. Min Act: -0.0000

Data Index: 615404 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1347767 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9329. Min Act: -0.0000

Data Index: 1136076 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1536319 (Python Code)

Max Activating Token Index: 219

Text #13

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7737. Min Act: -0.0000

Data Index: 673321 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7669. Min Act: -0.0000

Data Index: 846264 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1375760 (Python Code)

Max Activating Token Index: 333

Text #16

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1208789 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7807. Min Act: -0.0000

Data Index: 944195 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7546. Min Act: -0.0000

Data Index: 623301 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7157. Min Act: -0.0000

Data Index: 412670 (C4 (Web Text))

Max Activating Token Index: 506