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

Dataset: The Pile

Neuron 718 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: 0.2807. Min Range: -0.2807

Max Act: 0.2807. Min Act: -0.0000

Data Index: 641775 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1441. Min Act: -0.0000

Data Index: 406300 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1384183 (The Pile)

Max Activating Token Index: 745

Text #3

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1322058 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1899551 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1080273 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1226. Min Act: -0.0000

Data Index: 542611 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1280. Min Act: -0.0000

Data Index: 857719 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1267. Min Act: -0.0000

Data Index: 636679 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1057853 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1669466 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1184351 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1176. Min Act: -0.0000

Data Index: 678797 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1287167 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1343519 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1101. Min Act: -0.0000

Data Index: 831086 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1677885 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1883681 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1074. Min Act: -0.0000

Data Index: 555937 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.0978. Min Act: -0.0000

Data Index: 511560 (The Pile)

Max Activating Token Index: 359