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

Dataset: The Pile

Neuron 403 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: 0.7157. Min Range: -0.7157

Max Act: 0.7157. Min Act: -0.0000

Data Index: 48242 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.6415. Min Act: -0.0000

Data Index: 471193 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5968. Min Act: -0.0000

Data Index: 606508 (The Pile)

Max Activating Token Index: 213

Text #3

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5467. Min Act: -0.0000

Data Index: 885319 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5421. Min Act: -0.0000

Data Index: 104045 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5375. Min Act: -0.0000

Data Index: 578664 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1306989 (The Pile)

Max Activating Token Index: 368

Text #7

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1778260 (The Pile)

Max Activating Token Index: 818

Text #8

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1246003 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1526234 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5096. Min Act: -0.0000

Data Index: 76409 (The Pile)

Max Activating Token Index: 942

Text #11

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1807103 (The Pile)

Max Activating Token Index: 174

Text #12

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5017. Min Act: -0.0000

Data Index: 113171 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5129. Min Act: -0.0000

Data Index: 650879 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4780. Min Act: -0.0000

Data Index: 380312 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1801247 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5406. Min Act: -0.0000

Data Index: 937905 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4825. Min Act: -0.0000

Data Index: 208321 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1818655 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4821. Min Act: -0.0000

Data Index: 789147 (The Pile)

Max Activating Token Index: 248