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

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

Neuron 1045 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1852. Min Act: -0.0000

Data Index: 699962 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1994. Min Act: -0.0000

Data Index: 586872 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1325572 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1920. Min Act: -0.0000

Data Index: 87841 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1862. Min Act: -0.0000

Data Index: 516821 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1752. Min Act: -0.0000

Data Index: 238026 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1699. Min Act: -0.0000

Data Index: 97254 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1456. Min Act: -0.0000

Data Index: 67388 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1775. Min Act: -0.0001

Data Index: 126914 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1117145 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1113405 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1574. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1320. Min Act: -0.0000

Data Index: 98023 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1841. Min Act: -0.0000

Data Index: 211920 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1421548 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1709. Min Act: -0.0000

Data Index: 94166 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1543. Min Act: -0.0000

Data Index: 623477 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1405. Min Act: -0.0000

Data Index: 952673 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1397. Min Act: -0.0000

Data Index: 405314 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1452. Min Act: -0.0000

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 401