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

Dataset: The Pile

Neuron 3339 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7976. Min Act: -0.0000

Data Index: 601243 (The Pile)

Max Activating Token Index: 251

Text #1

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6887. Min Act: -0.0000

Data Index: 478485 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1143059 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6408. Min Act: -0.0000

Data Index: 271274 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6639. Min Act: -0.0000

Data Index: 263140 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1139439 (The Pile)

Max Activating Token Index: 341

Text #6

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1202135 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1028884 (The Pile)

Max Activating Token Index: 496

Text #8

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6239. Min Act: -0.0000

Data Index: 540387 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5690. Min Act: -0.0000

Data Index: 93991 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5824. Min Act: -0.0000

Data Index: 148649 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1697944 (The Pile)

Max Activating Token Index: 748

Text #12

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5774. Min Act: -0.0000

Data Index: 297208 (The Pile)

Max Activating Token Index: 410

Text #13

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5685. Min Act: -0.0000

Data Index: 658537 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5458. Min Act: -0.0000

Data Index: 330687 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1510048 (The Pile)

Max Activating Token Index: 665

Text #16

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1832803 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1485666 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5381. Min Act: -0.0000

Data Index: 557321 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1859023 (The Pile)

Max Activating Token Index: 441