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

Dataset: The Pile

Neuron 2386 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5140. Min Act: -0.0000

Data Index: 807175 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.6553. Min Act: -0.0000

Data Index: 375100 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1533765 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5200. Min Act: -0.0000

Data Index: 907430 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1230642 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1801855 (The Pile)

Max Activating Token Index: 474

Text #6

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.3768. Min Act: -0.0000

Data Index: 360648 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4787. Min Act: -0.0000

Data Index: 91033 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1599964 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.3522. Min Act: -0.0000

Data Index: 315743 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1608721 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1815381 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1169236 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1095137 (The Pile)

Max Activating Token Index: 706

Text #14

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1188075 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4172. Min Act: -0.0000

Data Index: 262264 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.3609. Min Act: -0.0000

Data Index: 620100 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1568538 (The Pile)

Max Activating Token Index: 509

Text #18

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4085. Min Act: -0.0000

Data Index: 437430 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.3065. Min Act: -0.0000

Data Index: 122864 (The Pile)

Max Activating Token Index: 58