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

Dataset: The Pile

Neuron 3807 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1253687 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1257347 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1675. Min Act: -0.0000

Data Index: 639292 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1578. Min Act: -0.0000

Data Index: 165666 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1579934 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1061624 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1316. Min Act: -0.0000

Data Index: 944235 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1621658 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1796572 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1297. Min Act: -0.0000

Data Index: 416699 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1247. Min Act: -0.0000

Data Index: 788511 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1364. Min Act: -0.0000

Data Index: 216984 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1814000 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1191. Min Act: -0.0000

Data Index: 867012 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1138. Min Act: -0.0000

Data Index: 526243 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1207. Min Act: -0.0000

Data Index: 426913 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1127. Min Act: -0.0000

Data Index: 559938 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1042. Min Act: -0.0000

Data Index: 347750 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1891161 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1170. Min Act: -0.0000

Data Index: 859525 (The Pile)

Max Activating Token Index: 698