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

Dataset: The Pile

Neuron 101 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: 3.0077. Min Range: -3.0077

Max Act: 3.0077. Min Act: -0.0000

Data Index: 1130669 (The Pile)

Max Activating Token Index: 106

Text #1

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.7804. Min Act: -0.0000

Data Index: 112719 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.6621. Min Act: -0.0000

Data Index: 908736 (The Pile)

Max Activating Token Index: 816

Text #3

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.4073. Min Act: -0.0000

Data Index: 791132 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.7586. Min Act: -0.0000

Data Index: 244830 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.5837. Min Act: -0.0000

Data Index: 988881 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.5269. Min Act: -0.0000

Data Index: 1367857 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.6270. Min Act: -0.0000

Data Index: 1281141 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.3230. Min Act: -0.0000

Data Index: 170531 (The Pile)

Max Activating Token Index: 171

Text #9

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.4407. Min Act: -0.0000

Data Index: 31989 (The Pile)

Max Activating Token Index: 204

Text #10

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.5421. Min Act: -0.0000

Data Index: 360726 (The Pile)

Max Activating Token Index: 889

Text #11

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.5341. Min Act: -0.0000

Data Index: 1633534 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.3637. Min Act: -0.0000

Data Index: 587540 (The Pile)

Max Activating Token Index: 911

Text #13

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.3285. Min Act: -0.0000

Data Index: 200705 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.2646. Min Act: -0.0000

Data Index: 279934 (The Pile)

Max Activating Token Index: 454

Text #15

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.2462. Min Act: -0.0000

Data Index: 1973547 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.3367. Min Act: -0.0000

Data Index: 289753 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.2177. Min Act: -0.0000

Data Index: 576694 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.1940. Min Act: -0.0000

Data Index: 757214 (The Pile)

Max Activating Token Index: 545

Text #19

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.3150. Min Act: -0.0000

Data Index: 566152 (The Pile)

Max Activating Token Index: 723