Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3915 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1141588 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1207817 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1616734 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1371036 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1285568 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8317. Min Act: -0.0000

Data Index: 20871 (The Pile)

Max Activating Token Index: 474

Text #6

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1291335 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8243. Min Act: -0.0000

Data Index: 7993 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1335952 (The Pile)

Max Activating Token Index: 656

Text #9

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1159977 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1732478 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1477027 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.7750. Min Act: -0.0000

Data Index: 617158 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8243. Min Act: -0.0000

Data Index: 983321 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8157. Min Act: -0.0000

Data Index: 28416 (The Pile)

Max Activating Token Index: 964

Text #15

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.7891. Min Act: -0.0000

Data Index: 105231 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1951081 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1525172 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1320511 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.7989. Min Act: -0.0000

Data Index: 86829 (The Pile)

Max Activating Token Index: 378