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

Dataset: The Pile

Neuron 2831 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1231828 (The Pile)

Max Activating Token Index: 725

Text #1

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1914178 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2698. Min Act: -0.0000

Data Index: 409863 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2396. Min Act: -0.0000

Data Index: 561867 (The Pile)

Max Activating Token Index: 583

Text #4

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1847670 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2795. Min Act: -0.0000

Data Index: 863375 (The Pile)

Max Activating Token Index: 321

Text #6

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1751944 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1221793 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1969899 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1225700 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2439. Min Act: -0.0000

Data Index: 268042 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1989176 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1579945 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1285347 (The Pile)

Max Activating Token Index: 699

Text #14

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2268. Min Act: -0.0000

Data Index: 677016 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1015277 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2155. Min Act: -0.0000

Data Index: 459604 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2095. Min Act: -0.0000

Data Index: 727642 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1586038 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1249862 (The Pile)

Max Activating Token Index: 631