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

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

Neuron 5517 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.4117. Min Act: -0.0001

Data Index: 1011954 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.4195. Min Act: -0.0001

Data Index: 425241 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1431. Min Act: -0.0001

Data Index: 640821 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.4298. Min Act: -0.0001

Data Index: 735664 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.2675. Min Act: -0.0001

Data Index: 380523 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.3023. Min Act: -0.0001

Data Index: 254046 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.2273. Min Act: -0.0001

Data Index: 1141958 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1243. Min Act: -0.0001

Data Index: 796596 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1050. Min Act: -0.0001

Data Index: 500573 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1941. Min Act: -0.0001

Data Index: 336279 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1445. Min Act: -0.0001

Data Index: 678182 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.0229. Min Act: -0.0001

Data Index: 235912 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1303. Min Act: -0.0001

Data Index: 959602 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.0341. Min Act: -0.0001

Data Index: 678064 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.0699. Min Act: -0.0001

Data Index: 916864 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.4298. Min Range: -1.4298

Max Act: 0.9927. Min Act: -0.0001

Data Index: 583365 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.0488. Min Act: -0.0001

Data Index: 288033 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 1.4298. Min Range: -1.4298

Max Act: 0.9817. Min Act: -0.0001

Data Index: 899534 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.0781. Min Act: -0.0001

Data Index: 1190570 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 1.4298. Min Range: -1.4298

Max Act: 0.9800. Min Act: -0.0001

Data Index: 819761 (C4 (Web Text))

Max Activating Token Index: 544