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

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

Neuron 3545 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.1580. Min Act: -0.0000

Data Index: 1272037 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1144166 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0935. Min Act: -0.0000

Data Index: 33239 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1282158 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0872. Min Act: -0.0000

Data Index: 551395 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0629. Min Act: -0.0000

Data Index: 808252 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9366. Min Act: -0.0000

Data Index: 818720 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9200. Min Act: -0.0000

Data Index: 684765 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1104340 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9535. Min Act: -0.0000

Data Index: 984051 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9221. Min Act: -0.0000

Data Index: 617628 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8923. Min Act: -0.0000

Data Index: 650947 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9243. Min Act: -0.0000

Data Index: 185141 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9074. Min Act: -0.0000

Data Index: 89035 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9176. Min Act: -0.0000

Data Index: 340723 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1152040 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1133908 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8480. Min Act: -0.0000

Data Index: 613548 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1205882 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1325646 (C4 (Web Text))

Max Activating Token Index: 762