Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1670 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.9413. Min Act: -0.0001

Data Index: 1262519 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7690. Min Act: -0.0001

Data Index: 101291 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.8558. Min Act: -0.0001

Data Index: 381901 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.8571. Min Act: -0.0001

Data Index: 1337815 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7337. Min Act: -0.0001

Data Index: 1072559 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7772. Min Act: -0.0001

Data Index: 37489 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7146. Min Act: -0.0001

Data Index: 188672 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7421. Min Act: -0.0001

Data Index: 1212009 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6728. Min Act: -0.0001

Data Index: 947163 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1058913 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7076. Min Act: -0.0001

Data Index: 683063 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6241. Min Act: -0.0001

Data Index: 222477 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6622. Min Act: -0.0001

Data Index: 563773 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7048. Min Act: -0.0001

Data Index: 645260 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6557. Min Act: -0.0001

Data Index: 1175604 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6434. Min Act: -0.0001

Data Index: 1315559 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6712. Min Act: -0.0001

Data Index: 697348 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6284. Min Act: -0.0001

Data Index: 164211 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6620. Min Act: -0.0001

Data Index: 669719 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7861. Min Act: -0.0001

Data Index: 534695 (C4 (Web Text))

Max Activating Token Index: 209