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

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

Neuron 4553 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: 0.3332. Min Range: -0.3332

Max Act: 0.3332. Min Act: -0.0000

Data Index: 1473021 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1510502 (Python Code)

Max Activating Token Index: 952

Text #2

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2275. Min Act: -0.0000

Data Index: 414372 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1347834 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2197. Min Act: -0.0000

Data Index: 783955 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1604. Min Act: -0.0000

Data Index: 307378 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1793. Min Act: -0.0000

Data Index: 747162 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1103014 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1761. Min Act: -0.0000

Data Index: 993071 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1108665 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1136232 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1827. Min Act: -0.0000

Data Index: 335462 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1804. Min Act: -0.0000

Data Index: 986731 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1874. Min Act: -0.0000

Data Index: 144955 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1930. Min Act: -0.0000

Data Index: 912845 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1969. Min Act: -0.0000

Data Index: 471104 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1928. Min Act: -0.0000

Data Index: 639383 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1806. Min Act: -0.0000

Data Index: 103559 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1648. Min Act: -0.0000

Data Index: 187215 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1838. Min Act: -0.0000

Data Index: 181291 (C4 (Web Text))

Max Activating Token Index: 14