Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1648 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.5234. Min Act: -0.0001

Data Index: 756328 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4332. Min Act: -0.0002

Data Index: 14247 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4323. Min Act: -0.0001

Data Index: 1285082 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4207. Min Act: -0.0002

Data Index: 269971 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4221. Min Act: -0.0002

Data Index: 1233958 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4056. Min Act: -0.0002

Data Index: 1173296 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3946. Min Act: -0.0001

Data Index: 131251 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3999. Min Act: -0.0002

Data Index: 1129298 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3850. Min Act: -0.0002

Data Index: 929137 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3760. Min Act: -0.0002

Data Index: 770089 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3704. Min Act: -0.0001

Data Index: 1329874 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3760. Min Act: -0.0002

Data Index: 57353 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3731. Min Act: -0.0002

Data Index: 460508 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3699. Min Act: -0.0002

Data Index: 1305741 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3783. Min Act: -0.0002

Data Index: 177877 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3658. Min Act: -0.0002

Data Index: 1281983 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3607. Min Act: -0.0001

Data Index: 1078800 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3634. Min Act: -0.0002

Data Index: 404745 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3485. Min Act: -0.0002

Data Index: 1016220 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3451. Min Act: -0.0002

Data Index: 429452 (C4 (Web Text))

Max Activating Token Index: 746