Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1063 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.5910. Min Act: -0.0000

Data Index: 494416 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1042940 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.5332. Min Act: -0.0000

Data Index: 785584 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.5420. Min Act: -0.0000

Data Index: 601366 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1044553 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4671. Min Act: -0.0000

Data Index: 791447 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4377. Min Act: 0.0000

Data Index: 1093891 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4435. Min Act: -0.0000

Data Index: 749837 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4668. Min Act: -0.0000

Data Index: 849017 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4339. Min Act: -0.0000

Data Index: 227818 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4302. Min Act: 0.0000

Data Index: 238290 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4311. Min Act: -0.0000

Data Index: 890030 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4570. Min Act: -0.0000

Data Index: 666298 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4373. Min Act: 0.0000

Data Index: 895075 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4467. Min Act: -0.0000

Data Index: 216613 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4343. Min Act: -0.0000

Data Index: 874222 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4443. Min Act: -0.0000

Data Index: 289674 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4073. Min Act: -0.0000

Data Index: 912629 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4347. Min Act: -0.0000

Data Index: 932339 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1327010 (C4 (Web Text))

Max Activating Token Index: 607