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

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

Neuron 5449 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: 4.0663. Min Range: -4.0663

Max Act: 4.0663. Min Act: -0.0000

Data Index: 531323 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8899. Min Act: -0.0000

Data Index: 1430582 (Python Code)

Max Activating Token Index: 157

Text #2

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8702. Min Act: -0.0000

Data Index: 1183623 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.2332. Min Act: -0.0000

Data Index: 93318 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.2169. Min Act: -0.0000

Data Index: 1103626 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.1893. Min Act: -0.0000

Data Index: 936822 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.1852. Min Act: -0.0000

Data Index: 790712 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.1638. Min Act: -0.0000

Data Index: 827276 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.1161. Min Act: -0.0000

Data Index: 908063 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.0515. Min Act: -0.0000

Data Index: 601447 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.1523. Min Act: -0.0000

Data Index: 1072457 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 4.0663. Min Range: -4.0663

Max Act: 2.9725. Min Act: -0.0000

Data Index: 729573 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 4.0663. Min Range: -4.0663

Max Act: 2.9494. Min Act: -0.0000

Data Index: 543679 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 4.0663. Min Range: -4.0663

Max Act: 2.7832. Min Act: -0.0000

Data Index: 449966 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 4.0663. Min Range: -4.0663

Max Act: 2.9195. Min Act: -0.0000

Data Index: 763814 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 4.0663. Min Range: -4.0663

Max Act: 2.8648. Min Act: -0.0000

Data Index: 476605 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 4.0663. Min Range: -4.0663

Max Act: 2.8874. Min Act: -0.0000

Data Index: 266010 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 4.0663. Min Range: -4.0663

Max Act: 2.8700. Min Act: -0.0000

Data Index: 518988 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.0001. Min Act: -0.0000

Data Index: 105700 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 4.0663. Min Range: -4.0663

Max Act: 2.8512. Min Act: -0.0000

Data Index: 404871 (C4 (Web Text))

Max Activating Token Index: 712