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

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

Neuron 439 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: 0.9096. Min Range: -0.9096

Max Act: 0.9096. Min Act: -0.0000

Data Index: 829921 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.9083. Min Act: -0.0000

Data Index: 566251 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8920. Min Act: -0.0000

Data Index: 270919 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8592. Min Act: -0.0000

Data Index: 97468 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1327650 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8375. Min Act: -0.0000

Data Index: 887262 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8126. Min Act: -0.0000

Data Index: 698059 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8315. Min Act: -0.0000

Data Index: 130345 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8516. Min Act: -0.0000

Data Index: 575466 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8292. Min Act: -0.0000

Data Index: 148657 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8340. Min Act: 0.0000

Data Index: 360941 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7538. Min Act: 0.0000

Data Index: 717259 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7889. Min Act: -0.0000

Data Index: 842856 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7905. Min Act: -0.0000

Data Index: 977329 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7954. Min Act: -0.0000

Data Index: 19678 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7768. Min Act: -0.0000

Data Index: 508192 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1328080 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7938. Min Act: -0.0000

Data Index: 380099 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1240412 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7228. Min Act: -0.0000

Data Index: 622284 (C4 (Web Text))

Max Activating Token Index: 120