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

Dataset: The Pile

Neuron 3438 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0000

Data Index: 967750 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0430. Min Act: -0.0000

Data Index: 70143 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0417. Min Act: -0.0000

Data Index: 1928291 (The Pile)

Max Activating Token Index: 716

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0387. Min Act: -0.0000

Data Index: 1134382 (The Pile)

Max Activating Token Index: 849

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0384. Min Act: -0.0000

Data Index: 1304582 (The Pile)

Max Activating Token Index: 671

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0367. Min Act: -0.0000

Data Index: 27980 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0369. Min Act: -0.0000

Data Index: 652507 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0363. Min Act: -0.0000

Data Index: 359764 (The Pile)

Max Activating Token Index: 567

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0361. Min Act: -0.0000

Data Index: 135084 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0360. Min Act: -0.0000

Data Index: 471735 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1620724 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0352. Min Act: 0.0000

Data Index: 882192 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0350. Min Act: -0.0000

Data Index: 353219 (The Pile)

Max Activating Token Index: 426

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0332. Min Act: -0.0000

Data Index: 287257 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1780954 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0344. Min Act: -0.0000

Data Index: 222450 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0340. Min Act: -0.0000

Data Index: 289769 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1870553 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0339. Min Act: -0.0000

Data Index: 593889 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1156083 (The Pile)

Max Activating Token Index: 441