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

Dataset: The Pile

Neuron 203 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: 0.7510. Min Range: -0.7510

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1696346 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1326410 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1307437 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1277452 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1964517 (The Pile)

Max Activating Token Index: 609

Text #5

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4966. Min Act: -0.0000

Data Index: 356690 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5959. Min Act: -0.0000

Data Index: 219176 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.7040. Min Act: -0.0000

Data Index: 935274 (The Pile)

Max Activating Token Index: 400

Text #8

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1062985 (The Pile)

Max Activating Token Index: 194

Text #9

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1036124 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1294572 (The Pile)

Max Activating Token Index: 609

Text #11

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1999365 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1285567 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1774538 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5678. Min Act: -0.0000

Data Index: 370396 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5246. Min Act: -0.0000

Data Index: 541159 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5513. Min Act: -0.0000

Data Index: 597172 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5836. Min Act: -0.0000

Data Index: 433064 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1772321 (The Pile)

Max Activating Token Index: 48

Text #19

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1116650 (The Pile)

Max Activating Token Index: 928