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

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

Neuron 2294 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: 0.7945. Min Range: -0.7945

Max Act: 0.7945. Min Act: -0.0001

Data Index: 946284 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6758. Min Act: -0.0001

Data Index: 150959 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7010. Min Act: -0.0001

Data Index: 370011 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6650. Min Act: -0.0001

Data Index: 875121 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6470. Min Act: -0.0001

Data Index: 671385 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6420. Min Act: -0.0001

Data Index: 450215 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6595. Min Act: -0.0001

Data Index: 531820 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5714. Min Act: -0.0001

Data Index: 24002 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6845. Min Act: -0.0001

Data Index: 214142 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6079. Min Act: -0.0001

Data Index: 305576 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6229. Min Act: -0.0001

Data Index: 734011 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5761. Min Act: -0.0001

Data Index: 615313 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5899. Min Act: -0.0001

Data Index: 416702 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5850. Min Act: -0.0001

Data Index: 745011 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5563. Min Act: -0.0001

Data Index: 607711 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5500. Min Act: -0.0001

Data Index: 36410 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5857. Min Act: -0.0001

Data Index: 501042 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5236. Min Act: -0.0001

Data Index: 552351 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5416. Min Act: -0.0001

Data Index: 649195 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5151. Min Act: -0.0001

Data Index: 497495 (C4 (Web Text))

Max Activating Token Index: 525