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

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

Neuron 3989 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1196963 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1320192 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.1629. Min Act: -0.0000

Data Index: 141953 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1323685 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.0750. Min Act: -0.0000

Data Index: 387887 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.0603. Min Act: -0.0000

Data Index: 909338 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.0504. Min Act: -0.0000

Data Index: 973256 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.0445. Min Act: -0.0000

Data Index: 640772 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.0286. Min Act: -0.0000

Data Index: 228746 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.0928. Min Act: -0.0000

Data Index: 538825 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1055502 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 1.3359. Min Range: -1.3359

Max Act: 0.9907. Min Act: -0.0000

Data Index: 809491 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 1.3359. Min Range: -1.3359

Max Act: 0.9190. Min Act: -0.0000

Data Index: 678652 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 1.3359. Min Range: -1.3359

Max Act: 0.9824. Min Act: -0.0000

Data Index: 903105 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.3359. Min Range: -1.3359

Max Act: 0.9736. Min Act: -0.0000

Data Index: 21916 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 1.3359. Min Range: -1.3359

Max Act: 0.9142. Min Act: -0.0000

Data Index: 129864 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 1.3359. Min Range: -1.3359

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1127554 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.3359. Min Range: -1.3359

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1270392 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 1.3359. Min Range: -1.3359

Max Act: 0.9368. Min Act: -0.0000

Data Index: 735367 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 1.3359. Min Range: -1.3359

Max Act: 0.9489. Min Act: -0.0000

Data Index: 640900 (C4 (Web Text))

Max Activating Token Index: 985