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

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

Neuron 3536 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.8956. Min Act: -0.0001

Data Index: 1231724 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.9205. Min Act: -0.0001

Data Index: 400048 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.7726. Min Act: -0.0001

Data Index: 782361 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.9005. Min Act: -0.0001

Data Index: 492311 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.6300. Min Act: -0.0001

Data Index: 102161 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.6667. Min Act: -0.0001

Data Index: 882498 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.6208. Min Act: -0.0001

Data Index: 1162475 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.6928. Min Act: -0.0001

Data Index: 1156011 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.6433. Min Act: -0.0001

Data Index: 596833 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.6361. Min Act: -0.0001

Data Index: 1001705 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.5184. Min Act: -0.0001

Data Index: 1118301 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.6324. Min Act: -0.0001

Data Index: 1355211 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.5487. Min Act: -0.0001

Data Index: 563585 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.5294. Min Act: -0.0001

Data Index: 320318 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.5298. Min Act: -0.0001

Data Index: 558295 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.5144. Min Act: -0.0001

Data Index: 628180 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.5213. Min Act: -0.0001

Data Index: 869160 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.5296. Min Act: -0.0001

Data Index: 380325 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.4433. Min Act: -0.0001

Data Index: 1278308 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 1.9205. Min Range: -1.9205

Max Act: 1.4716. Min Act: -0.0001

Data Index: 75503 (C4 (Web Text))

Max Activating Token Index: 236