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

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

Neuron 1608 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.8990. Min Act: -0.0000

Data Index: 641289 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.7597. Min Act: -0.0000

Data Index: 139112 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1044459 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.7434. Min Act: -0.0000

Data Index: 432482 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.7946. Min Act: -0.0000

Data Index: 360558 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.7054. Min Act: -0.0000

Data Index: 559426 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.7103. Min Act: 0.0000

Data Index: 431954 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.7088. Min Act: -0.0000

Data Index: 2289 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1075162 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.6811. Min Act: -0.0000

Data Index: 39046 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.7075. Min Act: -0.0000

Data Index: 272118 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.7003. Min Act: -0.0000

Data Index: 796921 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.6735. Min Act: -0.0000

Data Index: 708665 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.6288. Min Act: -0.0000

Data Index: 195565 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1262349 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.6790. Min Act: -0.0000

Data Index: 844278 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.6147. Min Act: -0.0000

Data Index: 874857 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.6265. Min Act: -0.0000

Data Index: 115136 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1332065 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.8990. Min Range: -0.8990

Max Act: 0.6200. Min Act: -0.0000

Data Index: 864150 (C4 (Web Text))

Max Activating Token Index: 896