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

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

Neuron 484 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: 0.1580. Min Range: -0.1580

Max Act: 0.1502. Min Act: -0.0002

Data Index: 478123 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1580. Min Act: -0.0002

Data Index: 876272 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1264. Min Act: -0.0002

Data Index: 821759 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1161. Min Act: -0.0002

Data Index: 318287 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1114221 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1219. Min Act: -0.0002

Data Index: 882991 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0991. Min Act: -0.0001

Data Index: 35827 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1125774 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0989. Min Act: -0.0001

Data Index: 661306 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1321665 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0823. Min Act: -0.0002

Data Index: 627885 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0954. Min Act: -0.0002

Data Index: 661603 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0988. Min Act: -0.0001

Data Index: 944232 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0934. Min Act: -0.0001

Data Index: 313905 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0929. Min Act: -0.0002

Data Index: 568244 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0889. Min Act: -0.0001

Data Index: 899581 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1214473 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0870. Min Act: -0.0002

Data Index: 699832 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1336687 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0918. Min Act: -0.0001

Data Index: 523550 (C4 (Web Text))

Max Activating Token Index: 149