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

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

Neuron 1053 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.6243. Min Act: -0.0000

Data Index: 447092 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.5080. Min Act: -0.0000

Data Index: 408744 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.2916. Min Act: -0.0000

Data Index: 9115 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.2589. Min Act: -0.0000

Data Index: 538209 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0957. Min Act: -0.0000

Data Index: 1099823 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0789. Min Act: -0.0000

Data Index: 1241825 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.1390. Min Act: -0.0000

Data Index: 75906 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 1.6243. Min Range: -1.6243

Max Act: 0.9696. Min Act: -0.0000

Data Index: 980646 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0213. Min Act: -0.0001

Data Index: 894274 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.1202. Min Act: -0.0000

Data Index: 316146 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0210. Min Act: -0.0000

Data Index: 1344649 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0239. Min Act: -0.0001

Data Index: 292724 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 1.6243. Min Range: -1.6243

Max Act: 0.9433. Min Act: -0.0000

Data Index: 370847 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 1.6243. Min Range: -1.6243

Max Act: 0.9818. Min Act: -0.0000

Data Index: 980507 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.6243. Min Range: -1.6243

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1135194 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.6243. Min Range: -1.6243

Max Act: 0.9950. Min Act: -0.0000

Data Index: 894118 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 1.6243. Min Range: -1.6243

Max Act: 0.9111. Min Act: -0.0000

Data Index: 596150 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.6243. Min Range: -1.6243

Max Act: 0.9604. Min Act: -0.0000

Data Index: 11775 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 1.6243. Min Range: -1.6243

Max Act: 0.9051. Min Act: -0.0000

Data Index: 246601 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 1.6243. Min Range: -1.6243

Max Act: 0.8699. Min Act: -0.0000

Data Index: 68862 (C4 (Web Text))

Max Activating Token Index: 165