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

Dataset: The Pile

Neuron 2207 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: 1.8977. Min Range: -1.8977

Max Act: 1.8977. Min Act: -0.0000

Data Index: 724157 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8712. Min Act: -0.0000

Data Index: 528330 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8227. Min Act: -0.0000

Data Index: 1614798 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7715. Min Act: -0.0000

Data Index: 1388544 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7176. Min Act: -0.0000

Data Index: 913987 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5644. Min Act: -0.0000

Data Index: 585088 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.6184. Min Act: -0.0000

Data Index: 912818 (The Pile)

Max Activating Token Index: 600

Text #7

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4868. Min Act: -0.0000

Data Index: 1661944 (The Pile)

Max Activating Token Index: 402

Text #8

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5446. Min Act: -0.0000

Data Index: 807985 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5245. Min Act: -0.0000

Data Index: 470069 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5040. Min Act: -0.0000

Data Index: 786906 (The Pile)

Max Activating Token Index: 337

Text #11

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3356. Min Act: -0.0000

Data Index: 1118453 (The Pile)

Max Activating Token Index: 941

Text #12

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4860. Min Act: -0.0000

Data Index: 976139 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4896. Min Act: -0.0000

Data Index: 462450 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4634. Min Act: -0.0000

Data Index: 701900 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1677330 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4503. Min Act: -0.0000

Data Index: 823066 (The Pile)

Max Activating Token Index: 705

Text #17

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5298. Min Act: -0.0000

Data Index: 72283 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5248. Min Act: -0.0000

Data Index: 489380 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1541313 (The Pile)

Max Activating Token Index: 932