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

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

Neuron 7 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.7626. Min Act: -0.0002

Data Index: 98774 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.4982. Min Act: -0.0002

Data Index: 493159 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.4679. Min Act: -0.0002

Data Index: 1248045 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.3972. Min Act: -0.0002

Data Index: 1076925 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.3765. Min Act: -0.0002

Data Index: 168629 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.4630. Min Act: -0.0002

Data Index: 1208301 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.3241. Min Act: -0.0002

Data Index: 1316 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.2667. Min Act: -0.0002

Data Index: 607313 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.3109. Min Act: -0.0002

Data Index: 583930 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.3620. Min Act: -0.0002

Data Index: 17484 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.3279. Min Act: -0.0002

Data Index: 531945 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.2014. Min Act: -0.0002

Data Index: 1172647 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.2272. Min Act: -0.0002

Data Index: 537786 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.2546. Min Act: -0.0002

Data Index: 992143 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.1925. Min Act: -0.0002

Data Index: 949558 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.1825. Min Act: -0.0002

Data Index: 1245536 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.1812. Min Act: -0.0002

Data Index: 68590 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.1532. Min Act: -0.0002

Data Index: 547152 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.0780. Min Act: -0.0002

Data Index: 1253637 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.7626. Min Range: -1.7626

Max Act: 1.1545. Min Act: -0.0002

Data Index: 176170 (C4 (Web Text))

Max Activating Token Index: 892