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

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

Neuron 1101 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.6033. Min Act: -0.0000

Data Index: 406490 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.5489. Min Act: 0.0000

Data Index: 469478 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1241399 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.5092. Min Act: -0.0000

Data Index: 666837 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4981. Min Act: -0.0000

Data Index: 805434 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4746. Min Act: -0.0000

Data Index: 623214 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1244374 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4698. Min Act: -0.0000

Data Index: 212436 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1219697 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4817. Min Act: -0.0000

Data Index: 703777 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4460. Min Act: -0.0000

Data Index: 289914 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1254810 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4545. Min Act: -0.0000

Data Index: 739243 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1071175 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4470. Min Act: -0.0000

Data Index: 690560 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4283. Min Act: -0.0000

Data Index: 948299 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4233. Min Act: -0.0000

Data Index: 634009 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4263. Min Act: -0.0000

Data Index: 342467 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1188238 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4304. Min Act: -0.0000

Data Index: 691002 (C4 (Web Text))

Max Activating Token Index: 720