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

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

Neuron 1815 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0441. Min Act: -0.0000

Data Index: 720032 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1339121 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8383. Min Act: -0.0000

Data Index: 530840 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1230929 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1281709 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1273729 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8195. Min Act: -0.0000

Data Index: 229283 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8395. Min Act: -0.0000

Data Index: 435005 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1079188 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7358. Min Act: -0.0000

Data Index: 500853 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7811. Min Act: -0.0000

Data Index: 941246 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7578. Min Act: -0.0000

Data Index: 325781 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7269. Min Act: -0.0000

Data Index: 305132 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7234. Min Act: -0.0000

Data Index: 965253 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7185. Min Act: -0.0000

Data Index: 985136 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.6974. Min Act: -0.0000

Data Index: 164921 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.6562. Min Act: -0.0000

Data Index: 455668 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1175380 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1046126 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7287. Min Act: 0.0000

Data Index: 525586 (C4 (Web Text))

Max Activating Token Index: 801