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

Dataset: The Pile

Neuron 3849 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1797196 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1248810 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.2081. Min Act: -0.0000

Data Index: 1931274 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.1215. Min Act: -0.0000

Data Index: 786593 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.1184. Min Act: -0.0000

Data Index: 502124 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1976282 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1678003 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1841420 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9821. Min Act: -0.0000

Data Index: 1463661 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9941. Min Act: -0.0000

Data Index: 598832 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1218770 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.8886. Min Act: -0.0000

Data Index: 377374 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9710. Min Act: -0.0000

Data Index: 822916 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1283060 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9586. Min Act: -0.0000

Data Index: 1245989 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1867765 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1135471 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9442. Min Act: -0.0000

Data Index: 844748 (The Pile)

Max Activating Token Index: 847

Text #18

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.8431. Min Act: -0.0000

Data Index: 652600 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1369578 (The Pile)

Max Activating Token Index: 552