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

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

Neuron 230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.4779. Min Act: -0.0001

Data Index: 389381 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.2266. Min Act: -0.0001

Data Index: 26639 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.1770. Min Act: -0.0001

Data Index: 693205 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.1441. Min Act: -0.0001

Data Index: 790066 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.0105. Min Act: -0.0001

Data Index: 820237 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.0290. Min Act: -0.0001

Data Index: 450232 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9581. Min Act: -0.0001

Data Index: 991274 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.8670. Min Act: -0.0001

Data Index: 183895 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9868. Min Act: -0.0001

Data Index: 930817 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.0703. Min Act: -0.0001

Data Index: 270274 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.0168. Min Act: -0.0001

Data Index: 751811 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.0713. Min Act: -0.0001

Data Index: 1156176 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9751. Min Act: -0.0001

Data Index: 1062038 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.0064. Min Act: -0.0001

Data Index: 1231998 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9533. Min Act: -0.0001

Data Index: 157280 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9815. Min Act: -0.0001

Data Index: 456278 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9636. Min Act: -0.0001

Data Index: 386784 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9634. Min Act: -0.0001

Data Index: 1133601 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9507. Min Act: -0.0001

Data Index: 441383 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.8087. Min Act: -0.0001

Data Index: 1029115 (C4 (Web Text))

Max Activating Token Index: 913