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

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

Neuron 919 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4558. Min Range: -1.4558

Max Act: 1.4558. Min Act: -0.0000

Data Index: 1114198 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 1.4558. Min Range: -1.4558

Max Act: 1.2339. Min Act: -0.0000

Data Index: 366898 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 1.4558. Min Range: -1.4558

Max Act: 1.0542. Min Act: -0.0000

Data Index: 856968 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 1.4558. Min Range: -1.4558

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1130469 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 1.4558. Min Range: -1.4558

Max Act: 1.0497. Min Act: -0.0000

Data Index: 1316376 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 1.4558. Min Range: -1.4558

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1219005 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 1.4558. Min Range: -1.4558

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1134765 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.4558. Min Range: -1.4558

Max Act: 1.0596. Min Act: -0.0000

Data Index: 887091 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 1.4558. Min Range: -1.4558

Max Act: 1.0021. Min Act: -0.0000

Data Index: 588362 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 1.4558. Min Range: -1.4558

Max Act: 0.9860. Min Act: -0.0000

Data Index: 626173 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 1.4558. Min Range: -1.4558

Max Act: 1.0255. Min Act: -0.0000

Data Index: 677655 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 1.4558. Min Range: -1.4558

Max Act: 0.9414. Min Act: -0.0000

Data Index: 242877 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.4558. Min Range: -1.4558

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1245635 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 1.4558. Min Range: -1.4558

Max Act: 0.9768. Min Act: -0.0000

Data Index: 805969 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 1.4558. Min Range: -1.4558

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1163063 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 1.4558. Min Range: -1.4558

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1326749 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.4558. Min Range: -1.4558

Max Act: 0.9560. Min Act: -0.0000

Data Index: 373235 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 1.4558. Min Range: -1.4558

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1240850 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.4558. Min Range: -1.4558

Max Act: 0.8927. Min Act: -0.0000

Data Index: 750970 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 1.4558. Min Range: -1.4558

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1065138 (C4 (Web Text))

Max Activating Token Index: 34