Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2404 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.6567. Min Act: -0.0001

Data Index: 340097 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.3455. Min Act: -0.0001

Data Index: 1015899 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.4281. Min Act: -0.0001

Data Index: 977338 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.3844. Min Act: -0.0001

Data Index: 726937 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.2324. Min Act: -0.0001

Data Index: 13056 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.3837. Min Act: -0.0001

Data Index: 1211465 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.2197. Min Act: -0.0001

Data Index: 1331577 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.1614. Min Act: -0.0001

Data Index: 645470 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.1329. Min Act: -0.0001

Data Index: 946742 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.0872. Min Act: -0.0001

Data Index: 1431185 (Python Code)

Max Activating Token Index: 413

Text #10

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.1185. Min Act: -0.0001

Data Index: 266457 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.1958. Min Act: -0.0001

Data Index: 1529288 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.1405. Min Act: -0.0001

Data Index: 1328425 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.0713. Min Act: -0.0001

Data Index: 760745 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.0345. Min Act: -0.0001

Data Index: 1407348 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1543927 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1150703 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.1599. Min Act: -0.0001

Data Index: 1604289 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.1588. Min Act: -0.0001

Data Index: 1591697 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 1.6567. Min Range: -1.6567

Max Act: 1.0400. Min Act: -0.0001

Data Index: 688063 (C4 (Web Text))

Max Activating Token Index: 607