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

Dataset: The Pile

Neuron 875 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: 1.6091. Min Range: -1.6091

Max Act: 1.6091. Min Act: -0.0000

Data Index: 1283134 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.4532. Min Act: -0.0000

Data Index: 1340355 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.4481. Min Act: -0.0000

Data Index: 1798025 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.4514. Min Act: -0.0000

Data Index: 762645 (The Pile)

Max Activating Token Index: 741

Text #4

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.2860. Min Act: -0.0000

Data Index: 788048 (The Pile)

Max Activating Token Index: 550

Text #5

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.3294. Min Act: -0.0000

Data Index: 1087323 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.2111. Min Act: -0.0000

Data Index: 754875 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.1483. Min Act: 0.0000

Data Index: 1488912 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.1412. Min Act: -0.0000

Data Index: 352364 (The Pile)

Max Activating Token Index: 195

Text #9

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1069918 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1252943 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.2379. Min Act: -0.0000

Data Index: 246625 (The Pile)

Max Activating Token Index: 946

Text #12

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1597984 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1277734 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1659805 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.1114. Min Act: -0.0000

Data Index: 338936 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0756. Min Act: -0.0000

Data Index: 641442 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1329930 (The Pile)

Max Activating Token Index: 945

Text #18

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1431116 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1124978 (The Pile)

Max Activating Token Index: 908