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

Dataset: The Pile

Neuron 4683 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: 1.9009. Min Range: -1.9009

Max Act: 1.9009. Min Act: -0.0000

Data Index: 1202173 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.6580. Min Act: -0.0000

Data Index: 1835248 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1442180 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.3749. Min Act: -0.0000

Data Index: 194448 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.4085. Min Act: -0.0000

Data Index: 1405336 (The Pile)

Max Activating Token Index: 873

Text #5

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.3167. Min Act: -0.0000

Data Index: 1140678 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.3168. Min Act: -0.0000

Data Index: 1365201 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.4643. Min Act: -0.0000

Data Index: 538830 (The Pile)

Max Activating Token Index: 745

Text #8

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.2934. Min Act: -0.0000

Data Index: 1938187 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.2881. Min Act: -0.0000

Data Index: 957337 (The Pile)

Max Activating Token Index: 341

Text #10

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1334617 (The Pile)

Max Activating Token Index: 883

Text #11

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.3431. Min Act: -0.0000

Data Index: 16667 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.3206. Min Act: -0.0000

Data Index: 696684 (The Pile)

Max Activating Token Index: 244

Text #13

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.3183. Min Act: -0.0000

Data Index: 90048 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.3143. Min Act: -0.0000

Data Index: 875039 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.2435. Min Act: -0.0000

Data Index: 477075 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.4002. Min Act: -0.0000

Data Index: 1471344 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.3030. Min Act: -0.0000

Data Index: 457231 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1853900 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 1.9009. Min Range: -1.9009

Max Act: 1.3471. Min Act: -0.0000

Data Index: 1226758 (The Pile)

Max Activating Token Index: 1005