Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3781 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.9295. Min Act: -0.0001

Data Index: 95202 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.3586. Min Act: -0.0001

Data Index: 591410 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.2500. Min Act: -0.0002

Data Index: 916554 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.9763. Min Act: -0.0002

Data Index: 782601 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 3.3586. Min Range: -3.3586

Max Act: 3.0747. Min Act: -0.0001

Data Index: 796829 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.7923. Min Act: -0.0001

Data Index: 702401 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.7015. Min Act: -0.0001

Data Index: 464438 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.8228. Min Act: -0.0001

Data Index: 528204 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.9193. Min Act: -0.0001

Data Index: 608514 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.6252. Min Act: -0.0002

Data Index: 986189 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.4799. Min Act: -0.0001

Data Index: 187240 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.8661. Min Act: -0.0001

Data Index: 209974 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.7235. Min Act: -0.0001

Data Index: 599228 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.6824. Min Act: -0.0002

Data Index: 1094941 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.8358. Min Act: -0.0002

Data Index: 964707 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.6569. Min Act: -0.0002

Data Index: 223762 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.4013. Min Act: -0.0002

Data Index: 650861 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.5245. Min Act: -0.0001

Data Index: 1141706 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.9757. Min Act: -0.0002

Data Index: 1205794 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 3.3586. Min Range: -3.3586

Max Act: 2.7465. Min Act: -0.0001

Data Index: 82091 (C4 (Web Text))

Max Activating Token Index: 367