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

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

Neuron 2189 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5243. Min Act: -0.0001

Data Index: 217188 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5997. Min Act: -0.0001

Data Index: 911979 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.3216. Min Act: -0.0001

Data Index: 268324 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5741. Min Act: -0.0001

Data Index: 225026 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4605. Min Act: -0.0001

Data Index: 1029268 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4273. Min Act: -0.0001

Data Index: 919012 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2836. Min Act: -0.0001

Data Index: 182235 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2346. Min Act: -0.0001

Data Index: 372201 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2869. Min Act: -0.0001

Data Index: 383759 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2232. Min Act: -0.0001

Data Index: 98317 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.1136. Min Act: -0.0001

Data Index: 915696 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.0868. Min Act: -0.0001

Data Index: 1135222 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.1025. Min Act: -0.0001

Data Index: 625476 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.1572. Min Act: -0.0001

Data Index: 915737 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.0051. Min Act: -0.0001

Data Index: 460352 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.0461. Min Act: -0.0001

Data Index: 147480 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.1202. Min Act: -0.0001

Data Index: 408678 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 1.5997. Min Range: -1.5997

Max Act: 0.9749. Min Act: -0.0001

Data Index: 150719 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 1.5997. Min Range: -1.5997

Max Act: 0.9980. Min Act: -0.0001

Data Index: 23603 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.5997. Min Range: -1.5997

Max Act: 0.9906. Min Act: -0.0001

Data Index: 300427 (C4 (Web Text))

Max Activating Token Index: 348