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

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

Neuron 5446 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.9624. Min Act: -0.0000

Data Index: 350200 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.8106. Min Act: -0.0000

Data Index: 11197 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.7625. Min Act: -0.0000

Data Index: 236747 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.4674. Min Act: -0.0000

Data Index: 1233104 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.4622. Min Act: -0.0000

Data Index: 205550 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.5229. Min Act: -0.0000

Data Index: 911264 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.3644. Min Act: -0.0000

Data Index: 1218508 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.2737. Min Act: -0.0000

Data Index: 479230 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.2762. Min Act: -0.0000

Data Index: 341746 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.3282. Min Act: -0.0000

Data Index: 910613 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.2451. Min Act: -0.0000

Data Index: 372950 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.2483. Min Act: -0.0000

Data Index: 640843 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.2959. Min Act: -0.0000

Data Index: 1244502 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.2166. Min Act: -0.0000

Data Index: 1289508 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.1996. Min Act: -0.0000

Data Index: 665863 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.1634. Min Act: -0.0000

Data Index: 3630 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.1596. Min Act: -0.0000

Data Index: 425385 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.1543. Min Act: -0.0000

Data Index: 515742 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.1433. Min Act: -0.0000

Data Index: 887879 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 1.9624. Min Range: -1.9624

Max Act: 1.1374. Min Act: -0.0000

Data Index: 96973 (C4 (Web Text))

Max Activating Token Index: 1020