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

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

Neuron 3575 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: 2.3194. Min Range: -2.3194

Max Act: 2.1803. Min Act: -0.0000

Data Index: 659023 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 2.3194. Min Range: -2.3194

Max Act: 2.3194. Min Act: -0.0000

Data Index: 1284890 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 2.3194. Min Range: -2.3194

Max Act: 2.1505. Min Act: -0.0000

Data Index: 341553 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 2.3194. Min Range: -2.3194

Max Act: 2.1791. Min Act: -0.0000

Data Index: 1285170 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 2.3194. Min Range: -2.3194

Max Act: 2.1213. Min Act: -0.0000

Data Index: 95857 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.9765. Min Act: -0.0000

Data Index: 642757 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.9433. Min Act: -0.0000

Data Index: 99096 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.9199. Min Act: -0.0000

Data Index: 508251 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.8104. Min Act: -0.0000

Data Index: 804804 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 2.3194. Min Range: -2.3194

Max Act: 2.0275. Min Act: -0.0000

Data Index: 74147 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.8895. Min Act: -0.0000

Data Index: 265561 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.8948. Min Act: -0.0000

Data Index: 718056 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.8847. Min Act: -0.0000

Data Index: 941043 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.7524. Min Act: -0.0000

Data Index: 827218 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.8420. Min Act: -0.0000

Data Index: 1185517 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.7298. Min Act: -0.0000

Data Index: 449852 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.8976. Min Act: -0.0000

Data Index: 38944 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.7712. Min Act: -0.0000

Data Index: 412066 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.7779. Min Act: -0.0000

Data Index: 775919 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.7231. Min Act: -0.0000

Data Index: 979077 (C4 (Web Text))

Max Activating Token Index: 919