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

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

Neuron 3199 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1587. Min Act: -0.0000

Data Index: 170574 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1112414 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0970. Min Act: -0.0000

Data Index: 468882 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1074. Min Act: -0.0000

Data Index: 622134 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0864. Min Act: -0.0000

Data Index: 7891 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0881. Min Act: -0.0000

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1151585 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0696. Min Act: -0.0000

Data Index: 655174 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0642. Min Act: -0.0000

Data Index: 646922 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0596. Min Act: -0.0000

Data Index: 942123 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0547. Min Act: -0.0001

Data Index: 764204 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0569. Min Act: -0.0000

Data Index: 216904 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0558. Min Act: -0.0000

Data Index: 361715 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0561. Min Act: -0.0000

Data Index: 501103 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0595. Min Act: -0.0000

Data Index: 260661 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0527. Min Act: -0.0000

Data Index: 1222240 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1578295 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1359969 (Python Code)

Max Activating Token Index: 595

Text #18

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1070841 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0467. Min Act: -0.0000

Data Index: 565254 (C4 (Web Text))

Max Activating Token Index: 913