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

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

Neuron 195 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.5595. Min Act: -0.0000

Data Index: 1606311 (Python Code)

Max Activating Token Index: 863

Text #1

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1014893 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.4831. Min Act: -0.0000

Data Index: 1498333 (Python Code)

Max Activating Token Index: 555

Text #3

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.4738. Min Act: -0.0000

Data Index: 1627243 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.2419. Min Act: -0.0000

Data Index: 512081 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.2926. Min Act: -0.0000

Data Index: 1259675 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.1354. Min Act: -0.0000

Data Index: 761823 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.1047. Min Act: -0.0000

Data Index: 721918 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1426088 (Python Code)

Max Activating Token Index: 660

Text #9

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0726. Min Act: -0.0000

Data Index: 666325 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0453. Min Act: -0.0000

Data Index: 810977 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1552103 (Python Code)

Max Activating Token Index: 626

Text #12

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0530. Min Act: -0.0000

Data Index: 289397 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 1.5595. Min Range: -1.5595

Max Act: 0.9919. Min Act: -0.0000

Data Index: 372921 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 1.5595. Min Range: -1.5595

Max Act: 0.9880. Min Act: -0.0000

Data Index: 483111 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0360. Min Act: -0.0000

Data Index: 182156 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0159. Min Act: -0.0000

Data Index: 772381 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 1.5595. Min Range: -1.5595

Max Act: 0.9523. Min Act: -0.0000

Data Index: 507583 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 1.5595. Min Range: -1.5595

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1532288 (Python Code)

Max Activating Token Index: 606

Text #19

Max Range: 1.5595. Min Range: -1.5595

Max Act: 0.8948. Min Act: -0.0000

Data Index: 313874 (C4 (Web Text))

Max Activating Token Index: 457