Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1674 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.5221. Min Act: -0.0001

Data Index: 1053565 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.5103. Min Act: -0.0001

Data Index: 1139111 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4924. Min Act: -0.0001

Data Index: 468133 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4702. Min Act: -0.0001

Data Index: 353837 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4701. Min Act: -0.0001

Data Index: 471653 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4739. Min Act: -0.0001

Data Index: 725032 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4404. Min Act: -0.0001

Data Index: 1340462 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4483. Min Act: -0.0001

Data Index: 767274 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4597. Min Act: -0.0001

Data Index: 321810 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4088. Min Act: -0.0001

Data Index: 1205877 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4278. Min Act: -0.0001

Data Index: 227363 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4294. Min Act: -0.0001

Data Index: 655104 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4164. Min Act: -0.0001

Data Index: 929214 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4132. Min Act: -0.0001

Data Index: 150469 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4219. Min Act: -0.0001

Data Index: 585606 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4238. Min Act: -0.0001

Data Index: 690900 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4279. Min Act: -0.0001

Data Index: 943345 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4270. Min Act: -0.0001

Data Index: 82310 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.3973. Min Act: -0.0001

Data Index: 587898 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.3646. Min Act: -0.0001

Data Index: 252632 (C4 (Web Text))

Max Activating Token Index: 607