Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1238 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.4925. Min Act: -0.0000

Data Index: 352549 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.4757. Min Act: -0.0000

Data Index: 417044 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.5775. Min Act: -0.0000

Data Index: 551816 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.2279. Min Act: -0.0000

Data Index: 556221 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.1842. Min Act: -0.0000

Data Index: 487883 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.0828. Min Act: -0.0000

Data Index: 1001090 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.0712. Min Act: -0.0000

Data Index: 143579 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.1746. Min Act: -0.0000

Data Index: 668884 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.0137. Min Act: -0.0000

Data Index: 316349 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.0726. Min Act: -0.0000

Data Index: 1086284 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.1884. Min Act: -0.0000

Data Index: 424323 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.0120. Min Act: -0.0000

Data Index: 700342 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.0247. Min Act: -0.0000

Data Index: 1230297 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.0093. Min Act: -0.0000

Data Index: 573713 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 2.5775. Min Range: -2.5775

Max Act: 1.9651. Min Act: -0.0000

Data Index: 139951 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 2.5775. Min Range: -2.5775

Max Act: 2.0567. Min Act: -0.0000

Data Index: 615826 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 2.5775. Min Range: -2.5775

Max Act: 1.8917. Min Act: -0.0000

Data Index: 681739 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 2.5775. Min Range: -2.5775

Max Act: 1.7382. Min Act: -0.0000

Data Index: 1076766 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 2.5775. Min Range: -2.5775

Max Act: 1.7389. Min Act: -0.0000

Data Index: 657160 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 2.5775. Min Range: -2.5775

Max Act: 1.8212. Min Act: -0.0000

Data Index: 839936 (C4 (Web Text))

Max Activating Token Index: 615