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

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

Neuron 4050 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: 1.2522. Min Range: -1.2522

Max Act: 1.2522. Min Act: -0.0001

Data Index: 1282263 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 1.2522. Min Range: -1.2522

Max Act: 1.0348. Min Act: -0.0001

Data Index: 1074921 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 1.2522. Min Range: -1.2522

Max Act: 1.0163. Min Act: -0.0001

Data Index: 939723 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.8610. Min Act: -0.0001

Data Index: 587725 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.9565. Min Act: -0.0001

Data Index: 171599 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.9569. Min Act: -0.0001

Data Index: 159459 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.9536. Min Act: -0.0001

Data Index: 811145 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.9338. Min Act: -0.0001

Data Index: 1196125 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.9673. Min Act: -0.0001

Data Index: 1187279 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.8461. Min Act: -0.0001

Data Index: 705324 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.8895. Min Act: -0.0001

Data Index: 782479 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.9484. Min Act: -0.0001

Data Index: 1249336 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.9061. Min Act: -0.0001

Data Index: 1047011 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.8890. Min Act: -0.0001

Data Index: 1036846 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.8996. Min Act: -0.0001

Data Index: 118927 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.8854. Min Act: -0.0001

Data Index: 772256 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.8009. Min Act: -0.0001

Data Index: 63179 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.8248. Min Act: -0.0001

Data Index: 876157 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.8153. Min Act: -0.0001

Data Index: 1267542 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 1.2522. Min Range: -1.2522

Max Act: 0.7868. Min Act: -0.0001

Data Index: 1256514 (C4 (Web Text))

Max Activating Token Index: 889