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

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

Neuron 4144 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1152. Min Range: -2.1152

Max Act: 2.1152. Min Act: -0.0001

Data Index: 926989 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 2.1152. Min Range: -2.1152

Max Act: 2.0791. Min Act: -0.0000

Data Index: 609730 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 2.1152. Min Range: -2.1152

Max Act: 2.0390. Min Act: -0.0001

Data Index: 1165516 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.9726. Min Act: -0.0000

Data Index: 452302 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.8951. Min Act: -0.0000

Data Index: 553669 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.9438. Min Act: -0.0000

Data Index: 1214951 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.9022. Min Act: -0.0000

Data Index: 511707 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.7583. Min Act: -0.0001

Data Index: 606302 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.9751. Min Act: -0.0001

Data Index: 759468 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.6395. Min Act: -0.0001

Data Index: 795782 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.7103. Min Act: -0.0000

Data Index: 110897 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.6071. Min Act: -0.0000

Data Index: 345386 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.7687. Min Act: -0.0000

Data Index: 1176228 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.7685. Min Act: -0.0000

Data Index: 374613 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.7588. Min Act: -0.0000

Data Index: 342806 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.6563. Min Act: -0.0001

Data Index: 55298 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.5621. Min Act: -0.0000

Data Index: 1219002 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.6616. Min Act: -0.0000

Data Index: 1261986 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.4657. Min Act: -0.0000

Data Index: 561120 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 2.1152. Min Range: -2.1152

Max Act: 1.5622. Min Act: -0.0001

Data Index: 566681 (C4 (Web Text))

Max Activating Token Index: 602