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

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

Neuron 1164 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1383797 (Python Code)

Max Activating Token Index: 536

Text #1

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1616452 (Python Code)

Max Activating Token Index: 96

Text #2

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1397819 (Python Code)

Max Activating Token Index: 962

Text #3

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1559604 (Python Code)

Max Activating Token Index: 619

Text #4

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1581526 (Python Code)

Max Activating Token Index: 642

Text #5

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0813. Min Act: -0.0001

Data Index: 512183 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1575990 (Python Code)

Max Activating Token Index: 600

Text #7

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0728. Min Act: -0.0001

Data Index: 835829 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1577790 (Python Code)

Max Activating Token Index: 773

Text #9

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1640631 (Python Code)

Max Activating Token Index: 855

Text #10

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1500665 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1543492 (Python Code)

Max Activating Token Index: 569

Text #12

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1436231 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1635082 (Python Code)

Max Activating Token Index: 488

Text #14

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1406865 (Python Code)

Max Activating Token Index: 27

Text #15

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1452519 (Python Code)

Max Activating Token Index: 378

Text #16

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0712. Min Act: -0.0001

Data Index: 963431 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1586843 (Python Code)

Max Activating Token Index: 919

Text #18

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1611489 (Python Code)

Max Activating Token Index: 925

Text #19

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1577340 (Python Code)

Max Activating Token Index: 219