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

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

Neuron 1373 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3104. Min Range: -1.3104

Max Act: 1.3104. Min Act: -0.0000

Data Index: 570881 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 1.3104. Min Range: -1.3104

Max Act: 1.1408. Min Act: -0.0000

Data Index: 456207 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 1.3104. Min Range: -1.3104

Max Act: 1.0836. Min Act: -0.0000

Data Index: 402081 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 1.3104. Min Range: -1.3104

Max Act: 1.1360. Min Act: -0.0000

Data Index: 660372 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 1.3104. Min Range: -1.3104

Max Act: 1.0400. Min Act: -0.0000

Data Index: 248920 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 1.3104. Min Range: -1.3104

Max Act: 1.0746. Min Act: -0.0000

Data Index: 675076 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.9819. Min Act: -0.0000

Data Index: 9027 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.9347. Min Act: -0.0000

Data Index: 258127 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.9899. Min Act: -0.0000

Data Index: 335879 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1358338 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1104631 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.9131. Min Act: -0.0000

Data Index: 886215 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8961. Min Act: -0.0000

Data Index: 133418 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1305478 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8824. Min Act: -0.0000

Data Index: 677839 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8924. Min Act: -0.0000

Data Index: 810001 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8360. Min Act: 0.0000

Data Index: 417230 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8535. Min Act: -0.0000

Data Index: 702457 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8663. Min Act: -0.0000

Data Index: 775132 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8029. Min Act: -0.0000

Data Index: 562580 (C4 (Web Text))

Max Activating Token Index: 290