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

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

Neuron 2237 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: 1.7723. Min Range: -1.7723

Max Act: 1.7723. Min Act: -0.0001

Data Index: 478419 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.5363. Min Act: -0.0001

Data Index: 907013 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.4048. Min Act: -0.0001

Data Index: 69225 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.5182. Min Act: -0.0001

Data Index: 83822 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.4308. Min Act: -0.0001

Data Index: 385032 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.4514. Min Act: -0.0001

Data Index: 1016792 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.4024. Min Act: -0.0001

Data Index: 749128 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.2515. Min Act: -0.0001

Data Index: 156363 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.2844. Min Act: -0.0001

Data Index: 1087751 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.1603. Min Act: -0.0001

Data Index: 195125 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.1671. Min Act: -0.0001

Data Index: 210113 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.1319. Min Act: -0.0001

Data Index: 1273512 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.1823. Min Act: -0.0001

Data Index: 115139 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.1283. Min Act: -0.0001

Data Index: 1175526 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.1015. Min Act: -0.0001

Data Index: 191845 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.1943. Min Act: -0.0001

Data Index: 1295788 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.1141. Min Act: -0.0001

Data Index: 162717 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.0871. Min Act: -0.0001

Data Index: 179198 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.1754. Min Act: -0.0001

Data Index: 607454 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 1.7723. Min Range: -1.7723

Max Act: 1.0986. Min Act: -0.0001

Data Index: 155569 (C4 (Web Text))

Max Activating Token Index: 87