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

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

Neuron 5427 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.7266. Min Act: -0.0000

Data Index: 1010995 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.1890. Min Act: -0.0000

Data Index: 478114 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.6340. Min Act: -0.0000

Data Index: 1218472 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.3563. Min Act: 0.0000

Data Index: 979794 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.2750. Min Act: -0.0000

Data Index: 114479 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.2576. Min Act: -0.0000

Data Index: 138322 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.2531. Min Act: -0.0000

Data Index: 479441 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.2269. Min Act: -0.0000

Data Index: 488395 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.2722. Min Act: -0.0000

Data Index: 1153734 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 2.7266. Min Range: -2.7266

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1351846 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.0681. Min Act: -0.0000

Data Index: 467618 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 2.7266. Min Range: -2.7266

Max Act: 1.9401. Min Act: -0.0000

Data Index: 1319246 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.0268. Min Act: -0.0000

Data Index: 104430 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.0206. Min Act: -0.0000

Data Index: 313805 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 2.7266. Min Range: -2.7266

Max Act: 1.9912. Min Act: -0.0000

Data Index: 93055 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.0858. Min Act: -0.0000

Data Index: 480698 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 2.7266. Min Range: -2.7266

Max Act: 1.9966. Min Act: -0.0000

Data Index: 125458 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 2.7266. Min Range: -2.7266

Max Act: 2.0854. Min Act: -0.0000

Data Index: 271370 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 2.7266. Min Range: -2.7266

Max Act: 1.9696. Min Act: -0.0000

Data Index: 74924 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 2.7266. Min Range: -2.7266

Max Act: 1.8348. Min Act: -0.0000

Data Index: 1185338 (C4 (Web Text))

Max Activating Token Index: 863