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

Dataset: The Pile

Neuron 4346 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: 0.3156. Min Range: -0.3156

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1927116 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1636346 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1589. Min Act: -0.0000

Data Index: 137768 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1712. Min Act: -0.0000

Data Index: 627839 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1727650 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1303. Min Act: -0.0000

Data Index: 225561 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1470940 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1320. Min Act: -0.0000

Data Index: 146355 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1462. Min Act: -0.0000

Data Index: 720283 (The Pile)

Max Activating Token Index: 770

Text #9

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1156. Min Act: -0.0000

Data Index: 550633 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1173. Min Act: -0.0000

Data Index: 684015 (The Pile)

Max Activating Token Index: 356

Text #11

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1659732 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.0874. Min Act: -0.0000

Data Index: 120173 (The Pile)

Max Activating Token Index: 794

Text #13

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1065242 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1203. Min Act: -0.0000

Data Index: 820090 (The Pile)

Max Activating Token Index: 710

Text #15

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1762159 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1081. Min Act: -0.0000

Data Index: 89152 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1301884 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1026. Min Act: -0.0000

Data Index: 767682 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1195030 (The Pile)

Max Activating Token Index: 955