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

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

Neuron 375 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1420. Min Range: -3.1420

Max Act: 3.1420. Min Act: -0.0000

Data Index: 265900 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.4937. Min Act: -0.0000

Data Index: 925570 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.5218. Min Act: -0.0000

Data Index: 847725 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.5126. Min Act: 0.0000

Data Index: 74946 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.2924. Min Act: -0.0000

Data Index: 265251 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.5074. Min Act: -0.0000

Data Index: 278222 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.2628. Min Act: -0.0000

Data Index: 1064558 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.2838. Min Act: -0.0000

Data Index: 116301 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.3122. Min Act: -0.0000

Data Index: 1294310 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.0880. Min Act: -0.0000

Data Index: 718893 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.1967. Min Act: -0.0000

Data Index: 1243925 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.1786. Min Act: -0.0000

Data Index: 296574 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.1433. Min Act: -0.0000

Data Index: 222674 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.1515. Min Act: -0.0000

Data Index: 788667 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.3675. Min Act: -0.0000

Data Index: 1145408 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.0189. Min Act: -0.0000

Data Index: 451538 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 3.1420. Min Range: -3.1420

Max Act: 2.0058. Min Act: -0.0000

Data Index: 936276 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 3.1420. Min Range: -3.1420

Max Act: 1.7605. Min Act: -0.0000

Data Index: 228034 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 3.1420. Min Range: -3.1420

Max Act: 1.8500. Min Act: -0.0000

Data Index: 739878 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 3.1420. Min Range: -3.1420

Max Act: 1.7652. Min Act: -0.0000

Data Index: 311887 (C4 (Web Text))

Max Activating Token Index: 330