Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 684 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1230274 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1446. Min Act: -0.0000

Data Index: 533273 (The Pile)

Max Activating Token Index: 536

Text #2

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1361. Min Act: -0.0000

Data Index: 294117 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1545866 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1176952 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1383838 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1237. Min Act: -0.0000

Data Index: 914383 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1280414 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1858878 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1143. Min Act: -0.0000

Data Index: 821260 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1164. Min Act: -0.0000

Data Index: 498857 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1238. Min Act: -0.0000

Data Index: 910892 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1745564 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1059. Min Act: -0.0000

Data Index: 871894 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1094. Min Act: -0.0000

Data Index: 785792 (The Pile)

Max Activating Token Index: 736

Text #15

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1220. Min Act: -0.0000

Data Index: 455150 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1054010 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1512280 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1075. Min Act: -0.0000

Data Index: 564411 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1509350 (The Pile)

Max Activating Token Index: 458