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

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

Neuron 1742 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.7105. Min Act: -0.0000

Data Index: 527143 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.7317. Min Act: -0.0000

Data Index: 30625 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6875. Min Act: -0.0000

Data Index: 615234 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1339720 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6193. Min Act: -0.0000

Data Index: 190001 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6336. Min Act: -0.0000

Data Index: 861278 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1637130 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5943. Min Act: -0.0000

Data Index: 9920 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1611899 (Python Code)

Max Activating Token Index: 139

Text #9

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6065. Min Act: -0.0000

Data Index: 415344 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1237875 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1578484 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1318485 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1524553 (Python Code)

Max Activating Token Index: 338

Text #14

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5670. Min Act: -0.0000

Data Index: 135834 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5521. Min Act: -0.0000

Data Index: 464220 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5162. Min Act: -0.0000

Data Index: 613337 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1024859 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1016670 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5215. Min Act: -0.0000

Data Index: 796946 (C4 (Web Text))

Max Activating Token Index: 222