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

Dataset: The Pile

Neuron 1556 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1177843 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.6192. Min Act: -0.0000

Data Index: 596358 (The Pile)

Max Activating Token Index: 424

Text #2

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.6159. Min Act: 0.0000

Data Index: 1513122 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5989. Min Act: -0.0000

Data Index: 937795 (The Pile)

Max Activating Token Index: 885

Text #4

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1041348 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5435. Min Act: -0.0000

Data Index: 379557 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5326. Min Act: -0.0000

Data Index: 501206 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5254. Min Act: 0.0001

Data Index: 409660 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1768449 (The Pile)

Max Activating Token Index: 474

Text #9

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4949. Min Act: -0.0000

Data Index: 61306 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5124. Min Act: 0.0000

Data Index: 1924267 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4915. Min Act: -0.0000

Data Index: 911501 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1712981 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4810. Min Act: -0.0000

Data Index: 125914 (The Pile)

Max Activating Token Index: 79

Text #14

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4867. Min Act: -0.0000

Data Index: 781078 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5034. Min Act: -0.0000

Data Index: 436396 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1397408 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1183257 (The Pile)

Max Activating Token Index: 606

Text #18

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4749. Min Act: -0.0000

Data Index: 721220 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1528822 (The Pile)

Max Activating Token Index: 327