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

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

Neuron 1217 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.9745. Min Act: -0.0001

Data Index: 863532 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 1.0390. Min Range: -1.0390

Max Act: 1.0390. Min Act: -0.0001

Data Index: 1067392 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.9495. Min Act: -0.0000

Data Index: 541820 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8451. Min Act: -0.0001

Data Index: 20848 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8868. Min Act: -0.0000

Data Index: 855109 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8557. Min Act: -0.0001

Data Index: 992882 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8336. Min Act: -0.0000

Data Index: 913215 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8084. Min Act: -0.0001

Data Index: 1177662 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8281. Min Act: -0.0001

Data Index: 155202 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8632. Min Act: -0.0001

Data Index: 1261231 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7784. Min Act: -0.0001

Data Index: 1273116 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7745. Min Act: -0.0000

Data Index: 970768 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7780. Min Act: -0.0001

Data Index: 188956 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7931. Min Act: -0.0001

Data Index: 1226701 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7947. Min Act: -0.0001

Data Index: 1212000 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8236. Min Act: -0.0001

Data Index: 686596 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8282. Min Act: -0.0001

Data Index: 26104 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7635. Min Act: -0.0000

Data Index: 508313 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8132. Min Act: -0.0001

Data Index: 180706 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8285. Min Act: -0.0001

Data Index: 863166 (C4 (Web Text))

Max Activating Token Index: 171