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

Dataset: The Pile

Neuron 630 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: 0.3174. Min Range: -0.3174

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1230127 (The Pile)

Max Activating Token Index: 74

Text #1

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1591761 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1272083 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1135088 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1449787 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2409. Min Act: -0.0000

Data Index: 184910 (The Pile)

Max Activating Token Index: 844

Text #6

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1422775 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2354. Min Act: -0.0000

Data Index: 829528 (The Pile)

Max Activating Token Index: 106

Text #8

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2289. Min Act: -0.0000

Data Index: 214499 (The Pile)

Max Activating Token Index: 139

Text #9

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1694955 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1457188 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1743339 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2333. Min Act: -0.0000

Data Index: 884655 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1908024 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2154. Min Act: -0.0000

Data Index: 7779 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2136. Min Act: -0.0000

Data Index: 334516 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1225418 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1465554 (The Pile)

Max Activating Token Index: 9

Text #18

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1130490 (The Pile)

Max Activating Token Index: 601

Text #19

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2129. Min Act: -0.0000

Data Index: 97221 (The Pile)

Max Activating Token Index: 303