Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2426 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1390. Min Range: -1.1390

Max Act: 1.1390. Min Act: -0.0001

Data Index: 972385 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.1390. Min Range: -1.1390

Max Act: 1.1054. Min Act: -0.0001

Data Index: 112967 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 1.1390. Min Range: -1.1390

Max Act: 1.0047. Min Act: -0.0001

Data Index: 449812 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.8881. Min Act: -0.0001

Data Index: 312385 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.9025. Min Act: -0.0001

Data Index: 168860 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.8824. Min Act: -0.0001

Data Index: 301047 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.8652. Min Act: -0.0001

Data Index: 848231 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.8136. Min Act: -0.0001

Data Index: 745395 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.7431. Min Act: -0.0001

Data Index: 1058458 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.7919. Min Act: -0.0001

Data Index: 245857 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.7782. Min Act: -0.0001

Data Index: 894769 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.7461. Min Act: -0.0001

Data Index: 1414439 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.7681. Min Act: -0.0001

Data Index: 368199 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.6883. Min Act: -0.0001

Data Index: 841079 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.7280. Min Act: -0.0001

Data Index: 1237619 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.7013. Min Act: -0.0001

Data Index: 219110 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.7129. Min Act: -0.0001

Data Index: 277633 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.6677. Min Act: -0.0001

Data Index: 1075182 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.6660. Min Act: -0.0001

Data Index: 612985 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.7111. Min Act: -0.0001

Data Index: 1158005 (C4 (Web Text))

Max Activating Token Index: 809