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

Dataset: The Pile

Neuron 3877 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: 0.4557. Min Range: -0.4557

Max Act: 0.4557. Min Act: -0.0000

Data Index: 352921 (The Pile)

Max Activating Token Index: 272

Text #1

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1900556 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1535981 (The Pile)

Max Activating Token Index: 357

Text #3

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2687. Min Act: -0.0000

Data Index: 82717 (The Pile)

Max Activating Token Index: 871

Text #4

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2420. Min Act: -0.0000

Data Index: 488466 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2019. Min Act: -0.0000

Data Index: 681299 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1223212 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1257669 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2346. Min Act: -0.0000

Data Index: 873650 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1270037 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1866812 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2031. Min Act: -0.0000

Data Index: 571224 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1097721 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2142. Min Act: -0.0000

Data Index: 73624 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2077. Min Act: -0.0000

Data Index: 239124 (The Pile)

Max Activating Token Index: 581

Text #15

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2006. Min Act: -0.0000

Data Index: 518567 (The Pile)

Max Activating Token Index: 550

Text #16

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1472246 (The Pile)

Max Activating Token Index: 893

Text #17

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2059. Min Act: -0.0000

Data Index: 336352 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1793271 (The Pile)

Max Activating Token Index: 790

Text #19

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1934549 (The Pile)

Max Activating Token Index: 128