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

Dataset: The Pile

Neuron 1687 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: 3.9143. Min Range: -3.9143

Max Act: 3.6044. Min Act: -0.0000

Data Index: 1267767 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.9143. Min Act: -0.0000

Data Index: 179251 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.4274. Min Act: -0.0000

Data Index: 1008240 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.5952. Min Act: -0.0000

Data Index: 705804 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.5432. Min Act: -0.0000

Data Index: 1413495 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7101. Min Act: -0.0000

Data Index: 1916972 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.5357. Min Act: -0.0000

Data Index: 65544 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.1752. Min Act: -0.0000

Data Index: 1875562 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.5765. Min Act: -0.0000

Data Index: 1227832 (The Pile)

Max Activating Token Index: 879

Text #9

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7654. Min Act: -0.0000

Data Index: 1778835 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.3529. Min Act: -0.0000

Data Index: 1272081 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.3218. Min Act: -0.0000

Data Index: 1160195 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.9756. Min Act: -0.0000

Data Index: 1100158 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.1295. Min Act: -0.0000

Data Index: 769495 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.2564. Min Act: -0.0000

Data Index: 1507357 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.2197. Min Act: -0.0000

Data Index: 1246036 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.2138. Min Act: -0.0000

Data Index: 487716 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.2185. Min Act: -0.0000

Data Index: 604680 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.0555. Min Act: -0.0000

Data Index: 462611 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.1869. Min Act: -0.0000

Data Index: 1976076 (The Pile)

Max Activating Token Index: 486