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

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

Neuron 4026 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.3365. Min Act: -0.0000

Data Index: 428259 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.3223. Min Act: -0.0000

Data Index: 36985 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2026. Min Act: -0.0000

Data Index: 530438 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1970. Min Act: -0.0000

Data Index: 914633 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0606. Min Act: -0.0000

Data Index: 362043 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1218268 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1615. Min Act: -0.0000

Data Index: 1260167 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1487. Min Act: -0.0000

Data Index: 773830 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1467. Min Act: -0.0000

Data Index: 223881 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0255. Min Act: -0.0000

Data Index: 532600 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0469. Min Act: -0.0000

Data Index: 514465 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9744. Min Act: -0.0000

Data Index: 69865 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1076489 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9647. Min Act: -0.0000

Data Index: 616855 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1122884 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9481. Min Act: -0.0000

Data Index: 948233 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0168. Min Act: -0.0000

Data Index: 764183 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0128. Min Act: -0.0000

Data Index: 419720 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9459. Min Act: 0.0000

Data Index: 156278 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9338. Min Act: -0.0000

Data Index: 566977 (C4 (Web Text))

Max Activating Token Index: 309