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

Dataset: The Pile

Neuron 2728 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.7087. Min Act: -0.0000

Data Index: 1364884 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.7177. Min Act: -0.0000

Data Index: 1796145 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.4893. Min Act: -0.0000

Data Index: 1649417 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.4628. Min Act: -0.0000

Data Index: 228167 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1928384 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.2665. Min Act: -0.0000

Data Index: 1353355 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.4009. Min Act: -0.0000

Data Index: 672642 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.3039. Min Act: -0.0000

Data Index: 191436 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1847. Min Act: -0.0000

Data Index: 260972 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.2158. Min Act: -0.0000

Data Index: 923354 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.3480. Min Act: -0.0000

Data Index: 1647202 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1645. Min Act: -0.0001

Data Index: 1550727 (The Pile)

Max Activating Token Index: 675

Text #12

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.0833. Min Act: -0.0000

Data Index: 1883700 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1160875 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.5453. Min Act: -0.0001

Data Index: 1404266 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1922. Min Act: -0.0000

Data Index: 842847 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1770. Min Act: -0.0000

Data Index: 1857094 (The Pile)

Max Activating Token Index: 7

Text #17

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1207245 (The Pile)

Max Activating Token Index: 973

Text #18

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.2225. Min Act: -0.0001

Data Index: 179753 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1503. Min Act: -0.0000

Data Index: 224194 (The Pile)

Max Activating Token Index: 793