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

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

Neuron 4475 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.6893. Min Act: -0.0000

Data Index: 850966 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.6369. Min Act: -0.0000

Data Index: 148942 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.8061. Min Act: -0.0000

Data Index: 100045 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.6772. Min Act: -0.0000

Data Index: 807501 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.6623. Min Act: -0.0000

Data Index: 453652 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.7510. Min Act: -0.0000

Data Index: 118302 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.6468. Min Act: -0.0000

Data Index: 1033120 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.6325. Min Act: -0.0000

Data Index: 1320273 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.5189. Min Act: -0.0000

Data Index: 595163 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.5259. Min Act: -0.0000

Data Index: 282045 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.5952. Min Act: -0.0000

Data Index: 807547 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.4850. Min Act: -0.0000

Data Index: 1206926 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.5854. Min Act: -0.0000

Data Index: 25575 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.5882. Min Act: -0.0000

Data Index: 1354213 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.4775. Min Act: -0.0000

Data Index: 291374 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.5710. Min Act: -0.0000

Data Index: 265223 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.6616. Min Act: -0.0000

Data Index: 749458 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.5558. Min Act: -0.0000

Data Index: 927926 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.5540. Min Act: -0.0000

Data Index: 933278 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.8061. Min Range: -1.8061

Max Act: 1.6482. Min Act: -0.0000

Data Index: 726471 (C4 (Web Text))

Max Activating Token Index: 81