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

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

Neuron 3168 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2598. Min Act: 0.0000

Data Index: 196794 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2492. Min Act: -0.0000

Data Index: 293810 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1939. Min Act: -0.0000

Data Index: 535285 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1986. Min Act: 0.0001

Data Index: 863878 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1236435 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1734. Min Act: -0.0000

Data Index: 496137 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1675. Min Act: 0.0000

Data Index: 875711 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1839. Min Act: -0.0000

Data Index: 820460 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1704. Min Act: -0.0000

Data Index: 456033 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1691. Min Act: -0.0000

Data Index: 194801 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1663. Min Act: -0.0000

Data Index: 357804 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1671. Min Act: 0.0001

Data Index: 620369 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1609. Min Act: -0.0000

Data Index: 906952 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1660. Min Act: 0.0000

Data Index: 609150 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1245100 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1624. Min Act: -0.0000

Data Index: 519660 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1350103 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1612. Min Act: -0.0000

Data Index: 722823 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1149044 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1598. Min Act: -0.0000

Data Index: 240490 (C4 (Web Text))

Max Activating Token Index: 254