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

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

Neuron 101 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.6818. Min Act: -0.0002

Data Index: 807091 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.6378. Min Act: -0.0003

Data Index: 292115 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.5357. Min Act: -0.0002

Data Index: 808886 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.5054. Min Act: -0.0002

Data Index: 896494 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4616. Min Act: -0.0002

Data Index: 623758 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4607. Min Act: -0.0002

Data Index: 27013 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4433. Min Act: -0.0002

Data Index: 876644 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4055. Min Act: -0.0002

Data Index: 569252 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4547. Min Act: -0.0002

Data Index: 354530 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4045. Min Act: -0.0002

Data Index: 76771 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3677. Min Act: -0.0002

Data Index: 483971 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3916. Min Act: -0.0002

Data Index: 245677 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3605. Min Act: -0.0003

Data Index: 343138 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3545. Min Act: -0.0002

Data Index: 104618 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3856. Min Act: -0.0002

Data Index: 290739 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3573. Min Act: -0.0002

Data Index: 171891 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3669. Min Act: -0.0003

Data Index: 1335267 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3340. Min Act: -0.0002

Data Index: 1259723 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3259. Min Act: -0.0002

Data Index: 1208859 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3206. Min Act: -0.0002

Data Index: 212628 (C4 (Web Text))

Max Activating Token Index: 738