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

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

Neuron 211 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0789. Min Act: -0.0002

Data Index: 755314 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0502. Min Act: -0.0002

Data Index: 251580 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1003647 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0474. Min Act: -0.0002

Data Index: 573161 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0476. Min Act: -0.0002

Data Index: 27157 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0491. Min Act: -0.0002

Data Index: 798873 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0454. Min Act: -0.0002

Data Index: 393673 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0467. Min Act: -0.0002

Data Index: 140034 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1183934 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1155375 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0435. Min Act: -0.0002

Data Index: 759107 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0446. Min Act: -0.0002

Data Index: 244382 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0428. Min Act: -0.0002

Data Index: 810671 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0414. Min Act: -0.0002

Data Index: 774994 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0420. Min Act: -0.0002

Data Index: 793429 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0417. Min Act: -0.0002

Data Index: 979588 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1174719 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0402. Min Act: -0.0002

Data Index: 799093 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0429. Min Act: -0.0002

Data Index: 580308 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1300695 (C4 (Web Text))

Max Activating Token Index: 830