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

Dataset: The Pile

Neuron 3034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7922. Min Act: -0.0000

Data Index: 803161 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.5401. Min Act: -0.0000

Data Index: 578389 (The Pile)

Max Activating Token Index: 255

Text #2

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.5093. Min Act: -0.0000

Data Index: 1926609 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.4796. Min Act: -0.0000

Data Index: 753590 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.3961. Min Act: -0.0000

Data Index: 990763 (The Pile)

Max Activating Token Index: 952

Text #5

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.3289. Min Act: -0.0000

Data Index: 655331 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.4402. Min Act: -0.0000

Data Index: 1778198 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.2630. Min Act: -0.0000

Data Index: 1234638 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.4393. Min Act: -0.0000

Data Index: 919842 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.4251. Min Act: -0.0000

Data Index: 150709 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.4345. Min Act: -0.0000

Data Index: 1793721 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.2481. Min Act: -0.0000

Data Index: 572059 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.3165. Min Act: -0.0000

Data Index: 744347 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.4848. Min Act: -0.0000

Data Index: 21339 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.3218. Min Act: -0.0000

Data Index: 1802434 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.1763. Min Act: -0.0000

Data Index: 1488979 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.3241. Min Act: -0.0000

Data Index: 44187 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.2852. Min Act: -0.0000

Data Index: 976368 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.1963. Min Act: -0.0000

Data Index: 608901 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.3123. Min Act: -0.0000

Data Index: 82417 (The Pile)

Max Activating Token Index: 230