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

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

Neuron 3261 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: 3.8868. Min Range: -3.8868

Max Act: 3.8722. Min Act: -0.0001

Data Index: 79599 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.7054. Min Act: -0.0001

Data Index: 450968 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.8868. Min Act: -0.0001

Data Index: 885982 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.7392. Min Act: -0.0001

Data Index: 961353 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.6550. Min Act: -0.0001

Data Index: 1330726 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.7314. Min Act: -0.0001

Data Index: 325612 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.8600. Min Act: -0.0001

Data Index: 995700 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.5795. Min Act: -0.0001

Data Index: 795248 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.8531. Min Act: -0.0001

Data Index: 252046 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.5067. Min Act: -0.0000

Data Index: 207660 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.2228. Min Act: -0.0000

Data Index: 1267974 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.2593. Min Act: -0.0001

Data Index: 182107 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.0873. Min Act: -0.0000

Data Index: 346866 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 3.8868. Min Range: -3.8868

Max Act: 2.9418. Min Act: -0.0000

Data Index: 418484 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.1783. Min Act: -0.0000

Data Index: 372332 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.1453. Min Act: -0.0001

Data Index: 235554 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.8868. Min Range: -3.8868

Max Act: 2.7868. Min Act: -0.0000

Data Index: 1164894 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 3.8868. Min Range: -3.8868

Max Act: 2.9946. Min Act: -0.0001

Data Index: 1330205 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.2406. Min Act: -0.0001

Data Index: 837652 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 3.8868. Min Range: -3.8868

Max Act: 3.1001. Min Act: -0.0001

Data Index: 244318 (C4 (Web Text))

Max Activating Token Index: 688