Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2098 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.5236. Min Act: -0.0000

Data Index: 633794 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.5712. Min Act: -0.0000

Data Index: 74233 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1592666 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1957113 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1073269 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3752. Min Act: -0.0000

Data Index: 345276 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1105260 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1680795 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4086. Min Act: -0.0000

Data Index: 699832 (The Pile)

Max Activating Token Index: 635

Text #9

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4384. Min Act: -0.0000

Data Index: 137419 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4105. Min Act: -0.0000

Data Index: 343590 (The Pile)

Max Activating Token Index: 800

Text #11

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1056213 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3540. Min Act: -0.0000

Data Index: 362571 (The Pile)

Max Activating Token Index: 49

Text #13

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4520. Min Act: -0.0000

Data Index: 711681 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1975898 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1274075 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1966675 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4013. Min Act: -0.0000

Data Index: 574588 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1860225 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1614811 (The Pile)

Max Activating Token Index: 205