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

Dataset: The Pile

Neuron 3824 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1845956 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.8675. Min Act: -0.0000

Data Index: 751559 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.9146. Min Act: -0.0000

Data Index: 950717 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.8355. Min Act: -0.0000

Data Index: 77328 (The Pile)

Max Activating Token Index: 195

Text #4

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1916520 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.8193. Min Act: -0.0000

Data Index: 246216 (The Pile)

Max Activating Token Index: 26

Text #6

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.8386. Min Act: -0.0000

Data Index: 760490 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1981692 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.8004. Min Act: -0.0000

Data Index: 932041 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7997. Min Act: -0.0000

Data Index: 23269 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1134776 (The Pile)

Max Activating Token Index: 482

Text #11

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7339. Min Act: -0.0000

Data Index: 544471 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7452. Min Act: -0.0000

Data Index: 232348 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1251159 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1643407 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1259723 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1327403 (The Pile)

Max Activating Token Index: 7

Text #17

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7047. Min Act: -0.0000

Data Index: 826107 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1761641 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 0.9146. Min Range: -0.9146

Max Act: 0.7122. Min Act: -0.0000

Data Index: 548660 (The Pile)

Max Activating Token Index: 677