Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2904 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.9158. Min Act: -0.0001

Data Index: 237147 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6846. Min Act: -0.0001

Data Index: 31672 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8267. Min Act: -0.0001

Data Index: 1341142 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7606. Min Act: -0.0001

Data Index: 355192 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7638. Min Act: -0.0001

Data Index: 1150708 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7927. Min Act: -0.0001

Data Index: 1100860 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7729. Min Act: -0.0001

Data Index: 1014599 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6740. Min Act: -0.0001

Data Index: 1352801 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7433. Min Act: -0.0001

Data Index: 816411 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6286. Min Act: -0.0001

Data Index: 340010 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6626. Min Act: -0.0001

Data Index: 1273565 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6177. Min Act: -0.0001

Data Index: 663284 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6857. Min Act: -0.0001

Data Index: 450691 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7610. Min Act: -0.0001

Data Index: 248329 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7247. Min Act: -0.0001

Data Index: 356722 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7156. Min Act: -0.0001

Data Index: 1287844 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.5493. Min Act: -0.0001

Data Index: 499135 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6365. Min Act: -0.0001

Data Index: 694044 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6851. Min Act: -0.0001

Data Index: 446761 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6752. Min Act: -0.0001

Data Index: 847873 (C4 (Web Text))

Max Activating Token Index: 860