Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 798 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1769353 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1195553 (The Pile)

Max Activating Token Index: 858

Text #2

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2680. Min Act: -0.0000

Data Index: 402390 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1111263 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2575. Min Act: -0.0000

Data Index: 612508 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2549. Min Act: 0.0000

Data Index: 78061 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1479190 (The Pile)

Max Activating Token Index: 484

Text #7

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1176344 (The Pile)

Max Activating Token Index: 866

Text #8

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2252. Min Act: -0.0000

Data Index: 976441 (The Pile)

Max Activating Token Index: 464

Text #9

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2265. Min Act: -0.0000

Data Index: 388030 (The Pile)

Max Activating Token Index: 226

Text #10

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1887756 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2182. Min Act: -0.0001

Data Index: 1264657 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2189. Min Act: -0.0000

Data Index: 255643 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1518532 (The Pile)

Max Activating Token Index: 916

Text #14

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1008678 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1800700 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1708785 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1999. Min Act: -0.0000

Data Index: 634267 (The Pile)

Max Activating Token Index: 594

Text #18

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2060. Min Act: -0.0000

Data Index: 500147 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1819. Min Act: -0.0000

Data Index: 95935 (The Pile)

Max Activating Token Index: 942