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

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

Neuron 476 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4694. Min Act: -0.0002

Data Index: 1652035 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4635. Min Act: -0.0002

Data Index: 1569366 (Python Code)

Max Activating Token Index: 432

Text #2

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4612. Min Act: -0.0002

Data Index: 1485503 (Python Code)

Max Activating Token Index: 696

Text #3

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4556. Min Act: -0.0002

Data Index: 1383869 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4485. Min Act: -0.0002

Data Index: 1581430 (Python Code)

Max Activating Token Index: 431

Text #5

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4506. Min Act: -0.0002

Data Index: 1644717 (Python Code)

Max Activating Token Index: 596

Text #6

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4372. Min Act: -0.0002

Data Index: 1598596 (Python Code)

Max Activating Token Index: 460

Text #7

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4397. Min Act: -0.0002

Data Index: 1455382 (Python Code)

Max Activating Token Index: 618

Text #8

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4429. Min Act: -0.0002

Data Index: 1482616 (Python Code)

Max Activating Token Index: 540

Text #9

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4427. Min Act: -0.0002

Data Index: 1562598 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4466. Min Act: -0.0002

Data Index: 1562299 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4374. Min Act: -0.0002

Data Index: 1446400 (Python Code)

Max Activating Token Index: 786

Text #12

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4309. Min Act: -0.0002

Data Index: 1560872 (Python Code)

Max Activating Token Index: 931

Text #13

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4327. Min Act: -0.0002

Data Index: 1651980 (Python Code)

Max Activating Token Index: 784

Text #14

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4373. Min Act: -0.0002

Data Index: 1367374 (Python Code)

Max Activating Token Index: 226

Text #15

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4310. Min Act: -0.0002

Data Index: 1603717 (Python Code)

Max Activating Token Index: 158

Text #16

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4238. Min Act: -0.0002

Data Index: 1625356 (Python Code)

Max Activating Token Index: 872

Text #17

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4236. Min Act: -0.0002

Data Index: 1606165 (Python Code)

Max Activating Token Index: 782

Text #18

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4153. Min Act: -0.0002

Data Index: 1616390 (Python Code)

Max Activating Token Index: 168

Text #19

Max Range: 0.4694. Min Range: -0.4694

Max Act: 0.4288. Min Act: -0.0002

Data Index: 1451526 (Python Code)

Max Activating Token Index: 331