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

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

Neuron 5479 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.7394. Min Act: -0.0001

Data Index: 312744 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.4941. Min Act: -0.0001

Data Index: 178221 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.1308. Min Act: -0.0001

Data Index: 56425 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.9688. Min Act: -0.0001

Data Index: 801149 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.9889. Min Act: -0.0001

Data Index: 537827 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.8132. Min Act: -0.0000

Data Index: 1194628 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.0039. Min Act: -0.0001

Data Index: 908410 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.8534. Min Act: -0.0001

Data Index: 933463 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.8457. Min Act: -0.0001

Data Index: 1300643 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.5607. Min Act: -0.0001

Data Index: 877513 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.0172. Min Act: -0.0001

Data Index: 661134 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.7884. Min Act: -0.0001

Data Index: 682902 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.7231. Min Act: -0.0001

Data Index: 315344 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.6342. Min Act: -0.0001

Data Index: 1349367 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.6908. Min Act: -0.0001

Data Index: 270594 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.7475. Min Act: -0.0001

Data Index: 803399 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.7171. Min Act: -0.0001

Data Index: 384994 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.4419. Min Act: -0.0001

Data Index: 1125930 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 3.7394. Min Range: -3.7394

Max Act: 2.7106. Min Act: -0.0001

Data Index: 1008917 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.0112. Min Act: -0.0001

Data Index: 1009125 (C4 (Web Text))

Max Activating Token Index: 892