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

Dataset: The Pile

Neuron 3354 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: 0.5435. Min Range: -0.5435

Max Act: 0.5435. Min Act: -0.0000

Data Index: 578192 (The Pile)

Max Activating Token Index: 315

Text #1

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1480843 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1034461 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1240277 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.5416. Min Act: -0.0000

Data Index: 622776 (The Pile)

Max Activating Token Index: 871

Text #5

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1848606 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4872. Min Act: -0.0000

Data Index: 522975 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4864. Min Act: -0.0000

Data Index: 947513 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4468. Min Act: -0.0000

Data Index: 767503 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4328. Min Act: -0.0000

Data Index: 687423 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4399. Min Act: -0.0000

Data Index: 179746 (The Pile)

Max Activating Token Index: 998

Text #11

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4357. Min Act: -0.0000

Data Index: 155164 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1101714 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1211665 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1534653 (The Pile)

Max Activating Token Index: 662

Text #15

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4217. Min Act: -0.0000

Data Index: 633838 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3779. Min Act: -0.0000

Data Index: 667840 (The Pile)

Max Activating Token Index: 944

Text #17

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4212. Min Act: -0.0000

Data Index: 244093 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4206. Min Act: -0.0000

Data Index: 108130 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1198031 (The Pile)

Max Activating Token Index: 191