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

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

Neuron 3644 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7192. Min Range: -4.7192

Max Act: 4.7192. Min Act: -0.0000

Data Index: 277024 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 4.7192. Min Range: -4.7192

Max Act: 4.6278. Min Act: -0.0000

Data Index: 84754 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 4.7192. Min Range: -4.7192

Max Act: 4.6701. Min Act: -0.0000

Data Index: 1296110 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 4.7192. Min Range: -4.7192

Max Act: 4.2965. Min Act: -0.0000

Data Index: 660097 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 4.7192. Min Range: -4.7192

Max Act: 2.0160. Min Act: -0.0000

Data Index: 49043 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.9521. Min Act: -0.0000

Data Index: 870640 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.8345. Min Act: -0.0000

Data Index: 636406 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.7868. Min Act: -0.0000

Data Index: 820749 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.9800. Min Act: -0.0000

Data Index: 1083098 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.8363. Min Act: -0.0000

Data Index: 323798 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.6781. Min Act: -0.0000

Data Index: 780050 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.6768. Min Act: -0.0000

Data Index: 542531 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.7688. Min Act: -0.0000

Data Index: 404965 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.7790. Min Act: -0.0000

Data Index: 817473 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.8557. Min Act: -0.0000

Data Index: 659397 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.6736. Min Act: -0.0000

Data Index: 181643 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.7531. Min Act: -0.0000

Data Index: 107066 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.6439. Min Act: -0.0000

Data Index: 731573 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.8267. Min Act: -0.0000

Data Index: 934995 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 4.7192. Min Range: -4.7192

Max Act: 1.7042. Min Act: -0.0000

Data Index: 1256128 (C4 (Web Text))

Max Activating Token Index: 916