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

Dataset: The Pile

Neuron 3481 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: 1.7919. Min Range: -1.7919

Max Act: 1.5542. Min Act: -0.0000

Data Index: 72505 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.7805. Min Act: -0.0000

Data Index: 357530 (The Pile)

Max Activating Token Index: 838

Text #2

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.7399. Min Act: -0.0000

Data Index: 700671 (The Pile)

Max Activating Token Index: 274

Text #3

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.7919. Min Act: -0.0000

Data Index: 1951993 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.6170. Min Act: -0.0000

Data Index: 984559 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.3406. Min Act: -0.0000

Data Index: 1362377 (The Pile)

Max Activating Token Index: 340

Text #6

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.4726. Min Act: -0.0000

Data Index: 1508353 (The Pile)

Max Activating Token Index: 849

Text #7

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.4478. Min Act: -0.0000

Data Index: 691177 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.4297. Min Act: -0.0000

Data Index: 415342 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1491018 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1160276 (The Pile)

Max Activating Token Index: 392

Text #11

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.3260. Min Act: -0.0000

Data Index: 763540 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.2078. Min Act: -0.0000

Data Index: 331653 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.3520. Min Act: -0.0000

Data Index: 1761212 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.3454. Min Act: -0.0000

Data Index: 1920996 (The Pile)

Max Activating Token Index: 156

Text #15

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1117800 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.5022. Min Act: -0.0000

Data Index: 1974624 (The Pile)

Max Activating Token Index: 156

Text #17

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.5739. Min Act: -0.0000

Data Index: 540014 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.2356. Min Act: -0.0000

Data Index: 362879 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 1.7919. Min Range: -1.7919

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1345888 (The Pile)

Max Activating Token Index: 785