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

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

Neuron 5902 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0626. Min Range: -2.0626

Max Act: 2.0626. Min Act: -0.0000

Data Index: 1538639 (Python Code)

Max Activating Token Index: 587

Text #1

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.8393. Min Act: -0.0001

Data Index: 1548612 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.5225. Min Act: -0.0000

Data Index: 1103797 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4967. Min Act: -0.0000

Data Index: 289993 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.5381. Min Act: -0.0000

Data Index: 937956 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4373. Min Act: -0.0000

Data Index: 1558056 (Python Code)

Max Activating Token Index: 542

Text #6

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4255. Min Act: -0.0000

Data Index: 41651 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.5854. Min Act: -0.0000

Data Index: 409342 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4040. Min Act: -0.0000

Data Index: 929002 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4902. Min Act: -0.0000

Data Index: 45087 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.3428. Min Act: -0.0000

Data Index: 534538 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4913. Min Act: -0.0000

Data Index: 356611 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4679. Min Act: -0.0000

Data Index: 1284335 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4749. Min Act: -0.0000

Data Index: 765435 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4256. Min Act: -0.0000

Data Index: 583947 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.3379. Min Act: -0.0000

Data Index: 206415 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4158. Min Act: -0.0000

Data Index: 612701 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4414. Min Act: -0.0000

Data Index: 610580 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.4926. Min Act: -0.0000

Data Index: 371385 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 2.0626. Min Range: -2.0626

Max Act: 1.3897. Min Act: -0.0000

Data Index: 199725 (C4 (Web Text))

Max Activating Token Index: 359