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

Dataset: The Pile

Neuron 65 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1860088 (The Pile)

Max Activating Token Index: 767

Text #1

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6218. Min Act: -0.0000

Data Index: 183259 (The Pile)

Max Activating Token Index: 740

Text #2

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5801. Min Act: -0.0000

Data Index: 73126 (The Pile)

Max Activating Token Index: 904

Text #3

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6124. Min Act: -0.0000

Data Index: 805211 (The Pile)

Max Activating Token Index: 637

Text #4

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1606485 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5737. Min Act: -0.0000

Data Index: 694935 (The Pile)

Max Activating Token Index: 581

Text #6

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1478244 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5494. Min Act: -0.0000

Data Index: 837978 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5273. Min Act: -0.0000

Data Index: 867930 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1569971 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5215. Min Act: -0.0000

Data Index: 434205 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1258116 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5006. Min Act: -0.0000

Data Index: 588369 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1428526 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5135. Min Act: -0.0000

Data Index: 848674 (The Pile)

Max Activating Token Index: 943

Text #15

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1275717 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4862. Min Act: -0.0000

Data Index: 877021 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5024. Min Act: -0.0000

Data Index: 87933 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1813248 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4996. Min Act: -0.0000

Data Index: 90238 (The Pile)

Max Activating Token Index: 743