Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 179 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1010919 (The Pile)

Max Activating Token Index: 908

Text #1

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.9292. Min Act: -0.0000

Data Index: 608892 (The Pile)

Max Activating Token Index: 981

Text #2

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1196387 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8071. Min Act: -0.0001

Data Index: 595360 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8287. Min Act: -0.0000

Data Index: 343091 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8094. Min Act: -0.0000

Data Index: 359034 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8542. Min Act: -0.0000

Data Index: 1037148 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8006. Min Act: -0.0000

Data Index: 723056 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1399948 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7726. Min Act: -0.0000

Data Index: 410894 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1359488 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1466383 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7128. Min Act: -0.0000

Data Index: 56375 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7066. Min Act: -0.0000

Data Index: 752224 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7200. Min Act: -0.0000

Data Index: 787786 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.6750. Min Act: -0.0001

Data Index: 40239 (The Pile)

Max Activating Token Index: 653

Text #16

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1310085 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7329. Min Act: -0.0000

Data Index: 291368 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7036. Min Act: -0.0001

Data Index: 531445 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1346592 (The Pile)

Max Activating Token Index: 621