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

Dataset: The Pile

Neuron 4211 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.7904. Min Act: -0.0000

Data Index: 228064 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1944100 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.3351. Min Act: -0.0000

Data Index: 484272 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1030961 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1133976 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.4002. Min Act: -0.0000

Data Index: 1980834 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.2690. Min Act: -0.0000

Data Index: 866344 (The Pile)

Max Activating Token Index: 22

Text #7

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.4051. Min Act: -0.0000

Data Index: 275302 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1141745 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.3120. Min Act: -0.0000

Data Index: 935994 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.0401. Min Act: -0.0000

Data Index: 26323 (The Pile)

Max Activating Token Index: 880

Text #11

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1813535 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.2522. Min Act: -0.0000

Data Index: 788147 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.3378. Min Act: -0.0000

Data Index: 1549876 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.2272. Min Act: -0.0000

Data Index: 750018 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.1202. Min Act: -0.0000

Data Index: 1001943 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.3224. Min Act: -0.0000

Data Index: 350315 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 1.7904. Min Range: -1.7904

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1766899 (The Pile)

Max Activating Token Index: 804

Text #18

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.2595. Min Act: -0.0000

Data Index: 785439 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.1208. Min Act: -0.0000

Data Index: 603694 (The Pile)

Max Activating Token Index: 807