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

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

Neuron 887 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0002

Data Index: 981928 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 743102 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 677006 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0003

Data Index: 582562 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 725372 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 526960 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0003

Data Index: 331660 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1627730 (Python Code)

Max Activating Token Index: 485

Text #8

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0003

Data Index: 1233842 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1485673 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 582958 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1421674 (Python Code)

Max Activating Token Index: 299

Text #12

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1013148 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 900 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1392835 (Python Code)

Max Activating Token Index: 119

Text #15

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1482331 (Python Code)

Max Activating Token Index: 773

Text #16

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1519130 (Python Code)

Max Activating Token Index: 800

Text #17

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0003

Data Index: 464959 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1532046 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 322716 (C4 (Web Text))

Max Activating Token Index: 375