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

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

Neuron 3107 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: 1.1408. Min Range: -1.1408

Max Act: 1.1408. Min Act: -0.0001

Data Index: 750397 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 1.1408. Min Range: -1.1408

Max Act: 1.1195. Min Act: -0.0001

Data Index: 606575 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.1408. Min Range: -1.1408

Max Act: 1.1011. Min Act: -0.0001

Data Index: 111944 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.1408. Min Range: -1.1408

Max Act: 1.0815. Min Act: -0.0001

Data Index: 1038032 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.1408. Min Range: -1.1408

Max Act: 1.0849. Min Act: -0.0001

Data Index: 1342988 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 1.1408. Min Range: -1.1408

Max Act: 1.0951. Min Act: -0.0001

Data Index: 1029895 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.1408. Min Range: -1.1408

Max Act: 1.0499. Min Act: -0.0001

Data Index: 258598 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 1.1408. Min Range: -1.1408

Max Act: 1.0240. Min Act: -0.0001

Data Index: 275501 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 1.1408. Min Range: -1.1408

Max Act: 1.0080. Min Act: -0.0001

Data Index: 398403 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.1408. Min Range: -1.1408

Max Act: 1.0082. Min Act: -0.0001

Data Index: 1141004 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.1408. Min Range: -1.1408

Max Act: 0.9645. Min Act: -0.0001

Data Index: 1317240 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 1.1408. Min Range: -1.1408

Max Act: 1.0173. Min Act: -0.0001

Data Index: 1251381 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.1408. Min Range: -1.1408

Max Act: 0.9624. Min Act: -0.0001

Data Index: 746307 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 1.1408. Min Range: -1.1408

Max Act: 0.9498. Min Act: -0.0001

Data Index: 389625 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 1.1408. Min Range: -1.1408

Max Act: 0.9455. Min Act: -0.0001

Data Index: 909631 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 1.1408. Min Range: -1.1408

Max Act: 0.9645. Min Act: -0.0001

Data Index: 686447 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 1.1408. Min Range: -1.1408

Max Act: 0.9765. Min Act: -0.0001

Data Index: 3674 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 1.1408. Min Range: -1.1408

Max Act: 0.9186. Min Act: -0.0001

Data Index: 792990 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.1408. Min Range: -1.1408

Max Act: 0.9094. Min Act: -0.0001

Data Index: 585912 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 1.1408. Min Range: -1.1408

Max Act: 0.9363. Min Act: -0.0001

Data Index: 608385 (C4 (Web Text))

Max Activating Token Index: 315