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

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

Neuron 368 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: 1.3541. Min Range: -1.3541

Max Act: 1.3541. Min Act: -0.0001

Data Index: 445699 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.3119. Min Act: -0.0001

Data Index: 394240 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.3288. Min Act: -0.0001

Data Index: 278585 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.3106. Min Act: -0.0001

Data Index: 408180 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.2910. Min Act: -0.0001

Data Index: 632753 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.2462. Min Act: -0.0001

Data Index: 186196 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.2051. Min Act: -0.0001

Data Index: 1243345 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1691. Min Act: -0.0001

Data Index: 87264 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1591. Min Act: -0.0001

Data Index: 533826 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1610. Min Act: -0.0001

Data Index: 18106 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1715. Min Act: -0.0001

Data Index: 328166 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1681. Min Act: -0.0001

Data Index: 348420 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1063. Min Act: -0.0001

Data Index: 459768 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1331. Min Act: -0.0001

Data Index: 409497 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1285257 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1616. Min Act: -0.0001

Data Index: 156422 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0836. Min Act: -0.0001

Data Index: 634337 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0738. Min Act: -0.0001

Data Index: 429560 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0751. Min Act: 0.0000

Data Index: 391100 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1051. Min Act: -0.0001

Data Index: 936261 (C4 (Web Text))

Max Activating Token Index: 281