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

Dataset: The Pile

Neuron 1207 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: 0.1648. Min Range: -0.1648

Max Act: 0.1648. Min Act: -0.0000

Data Index: 820182 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1498. Min Act: -0.0000

Data Index: 810599 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1740280 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1352590 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1441. Min Act: -0.0000

Data Index: 176632 (The Pile)

Max Activating Token Index: 760

Text #5

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1327. Min Act: -0.0000

Data Index: 537574 (The Pile)

Max Activating Token Index: 597

Text #6

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1719524 (The Pile)

Max Activating Token Index: 501

Text #7

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1221. Min Act: -0.0000

Data Index: 699013 (The Pile)

Max Activating Token Index: 279

Text #8

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1808694 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1240. Min Act: -0.0000

Data Index: 833531 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1206. Min Act: -0.0000

Data Index: 247933 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1133. Min Act: -0.0000

Data Index: 813808 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1354. Min Act: -0.0000

Data Index: 521144 (The Pile)

Max Activating Token Index: 829

Text #13

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1905775 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1182. Min Act: -0.0000

Data Index: 982802 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1130676 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1157354 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1087. Min Act: -0.0000

Data Index: 471142 (The Pile)

Max Activating Token Index: 543

Text #18

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1011. Min Act: -0.0000

Data Index: 50848 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1830329 (The Pile)

Max Activating Token Index: 128