Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4203 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.2129. Min Act: -0.0000

Data Index: 166133 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.7887. Min Act: -0.0000

Data Index: 608694 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.7622. Min Act: -0.0000

Data Index: 924447 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.6345. Min Act: -0.0000

Data Index: 885888 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.6267. Min Act: -0.0000

Data Index: 1117610 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.5873. Min Act: -0.0000

Data Index: 174840 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.5659. Min Act: -0.0000

Data Index: 44673 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.5564. Min Act: -0.0000

Data Index: 672950 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.5274. Min Act: -0.0000

Data Index: 529919 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.5259. Min Act: -0.0000

Data Index: 977152 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.5390. Min Act: -0.0000

Data Index: 386360 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.2421. Min Act: -0.0000

Data Index: 1225852 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.4656. Min Act: -0.0000

Data Index: 100759 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.4243. Min Act: -0.0000

Data Index: 828193 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.4235. Min Act: -0.0000

Data Index: 232250 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.4016. Min Act: -0.0000

Data Index: 707576 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.3994. Min Act: -0.0000

Data Index: 225464 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.3715. Min Act: -0.0000

Data Index: 655500 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.3685. Min Act: -0.0000

Data Index: 218589 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 3.2129. Min Range: -3.2129

Max Act: 2.3764. Min Act: -0.0000

Data Index: 107703 (C4 (Web Text))

Max Activating Token Index: 382