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

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

Neuron 824 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: -0.0003

Data Index: 605104 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0353. Min Act: -0.0003

Data Index: 677760 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0361. Min Act: -0.0004

Data Index: 35160 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0330. Min Act: -0.0003

Data Index: 697768 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0321. Min Act: -0.0003

Data Index: 302600 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0327. Min Act: -0.0003

Data Index: 493788 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0319. Min Act: -0.0004

Data Index: 60318 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0340. Min Act: -0.0004

Data Index: 929809 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1247400 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0327. Min Act: -0.0003

Data Index: 38313 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0306. Min Act: -0.0003

Data Index: 864661 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0306. Min Act: -0.0003

Data Index: 938727 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0311. Min Act: -0.0003

Data Index: 735945 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1317741 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0294. Min Act: -0.0003

Data Index: 477171 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0312. Min Act: -0.0003

Data Index: 792337 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0303. Min Act: -0.0003

Data Index: 973405 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0290. Min Act: -0.0003

Data Index: 684772 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0302. Min Act: -0.0003

Data Index: 501207 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1121918 (C4 (Web Text))

Max Activating Token Index: 806