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

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

Neuron 654 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0167. Min Range: -2.0167

Max Act: 2.0167. Min Act: -0.0000

Data Index: 1041101 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.8141. Min Act: -0.0000

Data Index: 36677 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.7061. Min Act: -0.0000

Data Index: 1228648 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.9162. Min Act: -0.0000

Data Index: 200269 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.7953. Min Act: -0.0000

Data Index: 521669 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.6925. Min Act: -0.0000

Data Index: 1147878 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.8808. Min Act: -0.0000

Data Index: 788386 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.6754. Min Act: -0.0000

Data Index: 787473 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.7621. Min Act: -0.0000

Data Index: 224049 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.6614. Min Act: -0.0000

Data Index: 1087994 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.7373. Min Act: -0.0000

Data Index: 245309 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.7322. Min Act: -0.0000

Data Index: 1215374 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.6174. Min Act: -0.0000

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.6936. Min Act: -0.0000

Data Index: 270305 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.5941. Min Act: -0.0000

Data Index: 1201519 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.6767. Min Act: -0.0000

Data Index: 1182305 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.5588. Min Act: -0.0000

Data Index: 373615 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.6469. Min Act: -0.0000

Data Index: 599391 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.5534. Min Act: -0.0000

Data Index: 690763 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 2.0167. Min Range: -2.0167

Max Act: 1.7453. Min Act: -0.0000

Data Index: 654646 (C4 (Web Text))

Max Activating Token Index: 888