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

Dataset: The Pile

Neuron 3604 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: 3.2195. Min Range: -3.2195

Max Act: 3.2195. Min Act: -0.0000

Data Index: 419215 (The Pile)

Max Activating Token Index: 354

Text #1

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.5806. Min Act: -0.0000

Data Index: 1515096 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.3845. Min Act: -0.0000

Data Index: 688841 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.2445. Min Act: -0.0000

Data Index: 1001444 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.2136. Min Act: -0.0000

Data Index: 621593 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.1016. Min Act: -0.0000

Data Index: 1483227 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.3035. Min Act: -0.0000

Data Index: 384320 (The Pile)

Max Activating Token Index: 728

Text #7

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.2544. Min Act: -0.0000

Data Index: 884707 (The Pile)

Max Activating Token Index: 275

Text #8

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.2772. Min Act: -0.0000

Data Index: 1956645 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.1073. Min Act: -0.0000

Data Index: 1971195 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.1870. Min Act: -0.0000

Data Index: 1743882 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.1575. Min Act: -0.0000

Data Index: 1230634 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.0400. Min Act: -0.0000

Data Index: 448285 (The Pile)

Max Activating Token Index: 762

Text #13

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.1458. Min Act: -0.0000

Data Index: 51824 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 3.2195. Min Range: -3.2195

Max Act: 1.9967. Min Act: -0.0000

Data Index: 310049 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 3.2195. Min Range: -3.2195

Max Act: 1.9717. Min Act: -0.0000

Data Index: 693310 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.1791. Min Act: -0.0000

Data Index: 854876 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 3.2195. Min Range: -3.2195

Max Act: 1.9070. Min Act: -0.0000

Data Index: 110932 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 3.2195. Min Range: -3.2195

Max Act: 1.9358. Min Act: -0.0000

Data Index: 673177 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 3.2195. Min Range: -3.2195

Max Act: 1.9199. Min Act: -0.0000

Data Index: 168480 (The Pile)

Max Activating Token Index: 488