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

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

Neuron 2198 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1344. Min Range: -1.1344

Max Act: 1.1344. Min Act: -0.0001

Data Index: 1044095 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.8572. Min Act: -0.0001

Data Index: 473088 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.8300. Min Act: -0.0000

Data Index: 726873 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.7632. Min Act: -0.0001

Data Index: 709715 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.7679. Min Act: -0.0001

Data Index: 384359 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.7365. Min Act: -0.0000

Data Index: 374770 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.6927. Min Act: -0.0000

Data Index: 843465 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.6361. Min Act: -0.0001

Data Index: 319315 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.6038. Min Act: -0.0001

Data Index: 915151 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.6159. Min Act: -0.0001

Data Index: 1316047 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.5376. Min Act: -0.0001

Data Index: 134674 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.5739. Min Act: -0.0001

Data Index: 1039107 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.5248. Min Act: -0.0001

Data Index: 827967 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.5310. Min Act: -0.0000

Data Index: 61464 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.5541. Min Act: -0.0001

Data Index: 528482 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.4745. Min Act: -0.0001

Data Index: 523326 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.4747. Min Act: -0.0000

Data Index: 91103 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1207147 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.4725. Min Act: -0.0000

Data Index: 948365 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.4551. Min Act: -0.0001

Data Index: 796858 (C4 (Web Text))

Max Activating Token Index: 57