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

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

Neuron 2744 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0001

Data Index: 410539 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0304. Min Act: -0.0001

Data Index: 897229 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0339. Min Act: -0.0001

Data Index: 354854 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0324. Min Act: -0.0001

Data Index: 701396 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0300. Min Act: -0.0001

Data Index: 234030 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1176256 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1316673 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0330. Min Act: -0.0001

Data Index: 387361 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0303. Min Act: -0.0001

Data Index: 407905 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0231. Min Act: -0.0001

Data Index: 266814 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0280. Min Act: -0.0001

Data Index: 361980 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1309898 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0286. Min Act: -0.0001

Data Index: 176053 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1023106 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0310. Min Act: -0.0001

Data Index: 992406 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0285. Min Act: -0.0001

Data Index: 189881 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0316. Min Act: -0.0001

Data Index: 612037 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1356902 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0269. Min Act: -0.0001

Data Index: 870740 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0297. Min Act: -0.0001

Data Index: 260707 (C4 (Web Text))

Max Activating Token Index: 164