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

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

Neuron 4706 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1334654 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1209179 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0507. Min Act: -0.0002

Data Index: 618850 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1216700 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1196635 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1195015 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0448. Min Act: -0.0002

Data Index: 593238 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0458. Min Act: -0.0002

Data Index: 430457 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0465. Min Act: -0.0003

Data Index: 773484 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1269235 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0524. Min Act: -0.0003

Data Index: 402392 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0392. Min Act: -0.0003

Data Index: 26404 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0424. Min Act: -0.0003

Data Index: 941811 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1329532 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0378. Min Act: -0.0003

Data Index: 765151 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0454. Min Act: -0.0003

Data Index: 779459 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1165366 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0433. Min Act: -0.0003

Data Index: 974930 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1234639 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1055962 (C4 (Web Text))

Max Activating Token Index: 403