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

Dataset: The Pile

Neuron 558 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.5630. Min Act: -0.0000

Data Index: 826515 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.5210. Min Act: -0.0000

Data Index: 945154 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4868. Min Act: -0.0000

Data Index: 414222 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1919662 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1122174 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4644. Min Act: -0.0000

Data Index: 767259 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1731959 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4576. Min Act: -0.0000

Data Index: 464981 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1856614 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4166. Min Act: -0.0000

Data Index: 216758 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1412044 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1576725 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4350. Min Act: -0.0000

Data Index: 925451 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1008975 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1499565 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1312592 (The Pile)

Max Activating Token Index: 153

Text #16

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1588892 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1644465 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1428727 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1705911 (The Pile)

Max Activating Token Index: 14