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

Dataset: The Pile

Neuron 4066 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: 0.3637. Min Range: -0.3637

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1880911 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1357872 (The Pile)

Max Activating Token Index: 305

Text #2

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2730. Min Act: -0.0000

Data Index: 983943 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2571. Min Act: -0.0000

Data Index: 178432 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2445. Min Act: -0.0000

Data Index: 812361 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1557731 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1456057 (The Pile)

Max Activating Token Index: 102

Text #7

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2118. Min Act: -0.0000

Data Index: 777356 (The Pile)

Max Activating Token Index: 243

Text #8

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2322. Min Act: -0.0000

Data Index: 47559 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1523879 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1304010 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1976. Min Act: -0.0000

Data Index: 186957 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2172. Min Act: -0.0000

Data Index: 136144 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1839218 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2015. Min Act: -0.0000

Data Index: 713061 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1989. Min Act: -0.0000

Data Index: 453515 (The Pile)

Max Activating Token Index: 197

Text #16

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1460873 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2165. Min Act: -0.0000

Data Index: 380845 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2241. Min Act: -0.0001

Data Index: 68934 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1950405 (The Pile)

Max Activating Token Index: 934