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

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

Neuron 3385 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0877. Min Range: -1.0877

Max Act: 1.0873. Min Act: -0.0001

Data Index: 1080930 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 1.0877. Min Range: -1.0877

Max Act: 1.0476. Min Act: -0.0001

Data Index: 906181 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 1.0877. Min Range: -1.0877

Max Act: 1.0774. Min Act: -0.0001

Data Index: 874275 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.0877. Min Range: -1.0877

Max Act: 1.0877. Min Act: -0.0001

Data Index: 617915 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.9505. Min Act: -0.0001

Data Index: 166885 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.9664. Min Act: -0.0001

Data Index: 425613 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 1.0877. Min Range: -1.0877

Max Act: 1.0196. Min Act: -0.0001

Data Index: 1014877 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.9012. Min Act: -0.0001

Data Index: 1095680 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.9490. Min Act: -0.0001

Data Index: 840806 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.9544. Min Act: -0.0001

Data Index: 332960 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.8528. Min Act: -0.0001

Data Index: 552581 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.9591. Min Act: -0.0001

Data Index: 1007577 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.9260. Min Act: -0.0001

Data Index: 1247950 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.9496. Min Act: -0.0001

Data Index: 204656 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.8677. Min Act: -0.0001

Data Index: 380334 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.8264. Min Act: -0.0001

Data Index: 633585 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.8403. Min Act: -0.0001

Data Index: 988915 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.8523. Min Act: -0.0001

Data Index: 448906 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.8584. Min Act: -0.0001

Data Index: 1320289 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 1.0877. Min Range: -1.0877

Max Act: 0.7741. Min Act: -0.0001

Data Index: 267843 (C4 (Web Text))

Max Activating Token Index: 242