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

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

Neuron 45 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8995. Min Act: -0.0001

Data Index: 869665 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8614. Min Act: -0.0001

Data Index: 73978 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.9025. Min Act: -0.0001

Data Index: 1149825 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8451. Min Act: -0.0002

Data Index: 1208169 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8193. Min Act: -0.0002

Data Index: 237433 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8637. Min Act: -0.0001

Data Index: 238446 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8086. Min Act: -0.0002

Data Index: 1310972 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8065. Min Act: -0.0002

Data Index: 937522 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8213. Min Act: -0.0002

Data Index: 613653 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7562. Min Act: -0.0001

Data Index: 670334 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7813. Min Act: -0.0001

Data Index: 639822 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7704. Min Act: -0.0001

Data Index: 420678 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7629. Min Act: -0.0002

Data Index: 333227 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7228. Min Act: -0.0001

Data Index: 537767 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7215. Min Act: -0.0001

Data Index: 251646 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7207. Min Act: -0.0001

Data Index: 947286 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6698. Min Act: -0.0001

Data Index: 66285 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7830. Min Act: -0.0002

Data Index: 67084 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7570. Min Act: -0.0002

Data Index: 61964 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7529. Min Act: -0.0002

Data Index: 306967 (C4 (Web Text))

Max Activating Token Index: 60