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

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

Neuron 4068 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.2447. Min Act: -0.0001

Data Index: 1004571 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1054070 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.2155. Min Act: -0.0000

Data Index: 667567 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.2272. Min Act: -0.0001

Data Index: 1040152 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.2148. Min Act: -0.0000

Data Index: 753464 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.2141. Min Act: -0.0000

Data Index: 534549 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1174076 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1968. Min Act: -0.0000

Data Index: 799718 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1876. Min Act: -0.0000

Data Index: 408432 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.2005. Min Act: 0.0000

Data Index: 174404 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1858. Min Act: -0.0000

Data Index: 590661 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1897. Min Act: -0.0000

Data Index: 484294 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1988. Min Act: -0.0001

Data Index: 426420 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1801. Min Act: -0.0001

Data Index: 116750 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1175083 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1369304 (Python Code)

Max Activating Token Index: 988

Text #16

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1425874 (Python Code)

Max Activating Token Index: 853

Text #17

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1552546 (Python Code)

Max Activating Token Index: 561

Text #18

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1791. Min Act: -0.0001

Data Index: 960055 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.2584. Min Range: -0.2584

Max Act: 0.1768. Min Act: -0.0000

Data Index: 856701 (C4 (Web Text))

Max Activating Token Index: 578