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

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

Neuron 5745 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6079. Min Range: -2.6079

Max Act: 2.6079. Min Act: -0.0000

Data Index: 365602 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.8355. Min Act: -0.0000

Data Index: 657248 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.4429. Min Act: -0.0000

Data Index: 464503 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.3712. Min Act: -0.0000

Data Index: 1249022 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.4042. Min Act: -0.0000

Data Index: 1548661 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.2409. Min Act: -0.0000

Data Index: 667900 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.2905. Min Act: -0.0000

Data Index: 197554 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1235432 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.2462. Min Act: -0.0000

Data Index: 235081 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.1867. Min Act: -0.0000

Data Index: 870146 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.1658. Min Act: -0.0000

Data Index: 818344 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.1558. Min Act: -0.0000

Data Index: 361239 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1272714 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.0331. Min Act: -0.0000

Data Index: 341592 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1087330 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1306803 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.0252. Min Act: -0.0000

Data Index: 1031701 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1338561 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 2.6079. Min Range: -2.6079

Max Act: 1.0083. Min Act: -0.0000

Data Index: 354642 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 2.6079. Min Range: -2.6079

Max Act: 0.9875. Min Act: -0.0000

Data Index: 901548 (C4 (Web Text))

Max Activating Token Index: 148