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

Dataset: The Pile

Neuron 2071 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: 0.5531. Min Range: -0.5531

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1455996 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1753782 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5486. Min Act: -0.0000

Data Index: 140003 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4805. Min Act: -0.0000

Data Index: 710635 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4773. Min Act: -0.0000

Data Index: 43935 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4274. Min Act: -0.0000

Data Index: 359190 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4637. Min Act: -0.0000

Data Index: 288148 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1192274 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1057185 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4267. Min Act: -0.0000

Data Index: 194721 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1427900 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4017. Min Act: -0.0000

Data Index: 780757 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4346. Min Act: -0.0000

Data Index: 209144 (The Pile)

Max Activating Token Index: 285

Text #13

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1143145 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4100. Min Act: -0.0000

Data Index: 542756 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1314332 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1323244 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1184606 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4119. Min Act: 0.0000

Data Index: 542468 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1327917 (The Pile)

Max Activating Token Index: 563