Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4395 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.3036. Min Act: -0.0000

Data Index: 5462 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2333. Min Act: -0.0000

Data Index: 301171 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2496. Min Act: -0.0000

Data Index: 336788 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1986. Min Act: -0.0000

Data Index: 690885 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1159208 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2016. Min Act: -0.0000

Data Index: 449910 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2012. Min Act: -0.0000

Data Index: 570669 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1191849 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1940. Min Act: -0.0000

Data Index: 612973 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1992. Min Act: -0.0000

Data Index: 860920 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2073. Min Act: -0.0000

Data Index: 932485 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1123608 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1193155 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1711. Min Act: -0.0000

Data Index: 789499 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1699. Min Act: -0.0000

Data Index: 661450 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1804. Min Act: -0.0000

Data Index: 615154 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1774. Min Act: -0.0000

Data Index: 639043 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1079900 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1251051 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1123777 (C4 (Web Text))

Max Activating Token Index: 765