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

Dataset: The Pile

Neuron 2561 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.3630. Min Act: -0.0000

Data Index: 636513 (The Pile)

Max Activating Token Index: 799

Text #1

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2430. Min Act: 0.0000

Data Index: 664577 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.0607. Min Act: 0.0000

Data Index: 1255184 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.9293. Min Act: -0.0000

Data Index: 657174 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.9240. Min Act: -0.0000

Data Index: 965463 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.8318. Min Act: 0.0000

Data Index: 369833 (The Pile)

Max Activating Token Index: 329

Text #6

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.5903. Min Act: -0.0000

Data Index: 1756079 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.6346. Min Act: -0.0000

Data Index: 1520040 (The Pile)

Max Activating Token Index: 811

Text #8

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.3886. Min Act: -0.0000

Data Index: 430560 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.6447. Min Act: -0.0000

Data Index: 1666558 (The Pile)

Max Activating Token Index: 71

Text #10

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.3179. Min Act: -0.0000

Data Index: 1635376 (The Pile)

Max Activating Token Index: 764

Text #11

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.5265. Min Act: -0.0000

Data Index: 532860 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.5254. Min Act: 0.0000

Data Index: 1717954 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.3551. Min Act: 0.0000

Data Index: 145567 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 3.3630. Min Range: -3.3630

Max Act: 1.9882. Min Act: 0.0000

Data Index: 625907 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 3.3630. Min Range: -3.3630

Max Act: 1.9483. Min Act: 0.0000

Data Index: 1374739 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.1359. Min Act: -0.0000

Data Index: 708552 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.1541. Min Act: -0.0000

Data Index: 1002262 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 3.3630. Min Range: -3.3630

Max Act: 1.9773. Min Act: -0.0000

Data Index: 1800709 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.0462. Min Act: -0.0000

Data Index: 1692072 (The Pile)

Max Activating Token Index: 61