Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 204 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0006

Data Index: 1205920 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0739. Min Act: -0.0005

Data Index: 322675 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0727. Min Act: -0.0006

Data Index: 1224139 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0741. Min Act: -0.0006

Data Index: 140778 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0724. Min Act: -0.0006

Data Index: 1036353 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0721. Min Act: -0.0006

Data Index: 756757 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0707. Min Act: -0.0006

Data Index: 977146 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0729. Min Act: -0.0006

Data Index: 820587 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0713. Min Act: -0.0006

Data Index: 1019354 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0694. Min Act: -0.0006

Data Index: 787202 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0660. Min Act: -0.0006

Data Index: 559144 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0666. Min Act: -0.0006

Data Index: 1159995 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0646. Min Act: -0.0006

Data Index: 750470 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0669. Min Act: -0.0006

Data Index: 1006870 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0681. Min Act: -0.0006

Data Index: 408265 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0708. Min Act: -0.0006

Data Index: 201930 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0679. Min Act: -0.0006

Data Index: 935586 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0623. Min Act: -0.0006

Data Index: 686075 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0634. Min Act: -0.0006

Data Index: 1209650 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0656. Min Act: -0.0006

Data Index: 952117 (C4 (Web Text))

Max Activating Token Index: 617