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

Dataset: The Pile

Neuron 133 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.4940. Min Act: -0.0000

Data Index: 1586888 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.5090. Min Act: -0.0000

Data Index: 293151 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.4957. Min Act: -0.0000

Data Index: 1565022 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.3235. Min Act: -0.0000

Data Index: 1797412 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.6736. Min Act: -0.0000

Data Index: 1925158 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.4380. Min Act: -0.0000

Data Index: 502731 (The Pile)

Max Activating Token Index: 1009

Text #6

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.5209. Min Act: -0.0000

Data Index: 991873 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.5072. Min Act: -0.0000

Data Index: 1356869 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.5307. Min Act: -0.0000

Data Index: 954685 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 3.6736. Min Range: -3.6736

Max Act: 2.9443. Min Act: -0.0000

Data Index: 153514 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.2498. Min Act: -0.0000

Data Index: 1649066 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.2224. Min Act: -0.0000

Data Index: 639220 (The Pile)

Max Activating Token Index: 379

Text #12

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.4917. Min Act: -0.0000

Data Index: 907869 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.3539. Min Act: -0.0000

Data Index: 1110149 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.1683. Min Act: -0.0000

Data Index: 850115 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.4782. Min Act: -0.0000

Data Index: 449736 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.4764. Min Act: -0.0000

Data Index: 1879148 (The Pile)

Max Activating Token Index: 752

Text #17

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.1386. Min Act: -0.0000

Data Index: 967017 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.2553. Min Act: -0.0000

Data Index: 1319461 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 3.6736. Min Range: -3.6736

Max Act: 3.5790. Min Act: -0.0000

Data Index: 1256806 (The Pile)

Max Activating Token Index: 384