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

Dataset: The Pile

Neuron 3043 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: 8.6474. Min Range: -8.6474

Max Act: 8.5605. Min Act: -0.0000

Data Index: 1234065 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 8.6474. Min Range: -8.6474

Max Act: 8.6474. Min Act: -0.0000

Data Index: 1120285 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 8.6474. Min Range: -8.6474

Max Act: 8.4127. Min Act: -0.0000

Data Index: 676249 (The Pile)

Max Activating Token Index: 368

Text #3

Max Range: 8.6474. Min Range: -8.6474

Max Act: 7.7042. Min Act: -0.0000

Data Index: 1058225 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 8.6474. Min Range: -8.6474

Max Act: 7.8683. Min Act: -0.0000

Data Index: 1551749 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 8.6474. Min Range: -8.6474

Max Act: 7.0535. Min Act: -0.0000

Data Index: 839327 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 8.6474. Min Range: -8.6474

Max Act: 6.9886. Min Act: -0.0000

Data Index: 1081712 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 8.6474. Min Range: -8.6474

Max Act: 7.1907. Min Act: -0.0000

Data Index: 173330 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 8.6474. Min Range: -8.6474

Max Act: 7.1234. Min Act: -0.0000

Data Index: 417178 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 8.6474. Min Range: -8.6474

Max Act: 6.9015. Min Act: -0.0000

Data Index: 800411 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 8.6474. Min Range: -8.6474

Max Act: 7.1498. Min Act: -0.0000

Data Index: 1638013 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 8.6474. Min Range: -8.6474

Max Act: 6.9041. Min Act: -0.0000

Data Index: 1100210 (The Pile)

Max Activating Token Index: 234

Text #12

Max Range: 8.6474. Min Range: -8.6474

Max Act: 7.4661. Min Act: -0.0000

Data Index: 1360161 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 8.6474. Min Range: -8.6474

Max Act: 7.1054. Min Act: -0.0000

Data Index: 62008 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 8.6474. Min Range: -8.6474

Max Act: 6.8906. Min Act: -0.0000

Data Index: 1504536 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 8.6474. Min Range: -8.6474

Max Act: 6.9147. Min Act: -0.0000

Data Index: 1152934 (The Pile)

Max Activating Token Index: 759

Text #16

Max Range: 8.6474. Min Range: -8.6474

Max Act: 7.1131. Min Act: -0.0000

Data Index: 1724021 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 8.6474. Min Range: -8.6474

Max Act: 6.8797. Min Act: -0.0000

Data Index: 1147636 (The Pile)

Max Activating Token Index: 310

Text #18

Max Range: 8.6474. Min Range: -8.6474

Max Act: 6.8425. Min Act: -0.0000

Data Index: 495712 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 8.6474. Min Range: -8.6474

Max Act: 6.6735. Min Act: -0.0000

Data Index: 1478927 (The Pile)

Max Activating Token Index: 273