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

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

Neuron 4453 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2809. Min Range: -3.2809

Max Act: 3.2809. Min Act: -0.0000

Data Index: 737536 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 3.2809. Min Range: -3.2809

Max Act: 3.0236. Min Act: -0.0000

Data Index: 492032 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.8572. Min Act: -0.0000

Data Index: 125065 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.6424. Min Act: -0.0000

Data Index: 812441 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.7485. Min Act: -0.0000

Data Index: 287726 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.4420. Min Act: -0.0000

Data Index: 96089 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.7288. Min Act: -0.0000

Data Index: 305773 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.3701. Min Act: -0.0000

Data Index: 515194 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.5113. Min Act: -0.0000

Data Index: 901111 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.2484. Min Act: -0.0000

Data Index: 1290787 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.2295. Min Act: -0.0000

Data Index: 64674 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.2235. Min Act: -0.0000

Data Index: 117978 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.1653. Min Act: -0.0000

Data Index: 1049006 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.2342. Min Act: -0.0000

Data Index: 568296 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.0933. Min Act: -0.0000

Data Index: 460894 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.0824. Min Act: -0.0000

Data Index: 1124826 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.1492. Min Act: -0.0000

Data Index: 469839 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 3.2809. Min Range: -3.2809

Max Act: 1.9972. Min Act: -0.0000

Data Index: 730471 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 3.2809. Min Range: -3.2809

Max Act: 1.8749. Min Act: -0.0000

Data Index: 367469 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 3.2809. Min Range: -3.2809

Max Act: 2.0361. Min Act: -0.0000

Data Index: 1354737 (C4 (Web Text))

Max Activating Token Index: 887