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

Dataset: The Pile

Neuron 2879 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.9086. Min Act: -0.0000

Data Index: 1888843 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.3277. Min Act: -0.0000

Data Index: 1806525 (The Pile)

Max Activating Token Index: 565

Text #2

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.4488. Min Act: -0.0000

Data Index: 591679 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.3853. Min Act: -0.0000

Data Index: 169917 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1016507 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.3395. Min Act: -0.0000

Data Index: 298124 (The Pile)

Max Activating Token Index: 277

Text #6

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.1367. Min Act: -0.0000

Data Index: 455203 (The Pile)

Max Activating Token Index: 930

Text #7

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1265235 (The Pile)

Max Activating Token Index: 426

Text #8

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.1011. Min Act: -0.0000

Data Index: 360609 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.2103. Min Act: -0.0000

Data Index: 661363 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.1052. Min Act: -0.0000

Data Index: 97554 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1795688 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.0436. Min Act: -0.0000

Data Index: 517674 (The Pile)

Max Activating Token Index: 694

Text #13

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.2446. Min Act: -0.0000

Data Index: 747174 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1478510 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.0934. Min Act: -0.0000

Data Index: 421883 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 1.9086. Min Range: -1.9086

Max Act: 0.9887. Min Act: -0.0000

Data Index: 665464 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1013409 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.1949. Min Act: -0.0000

Data Index: 116294 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.9086. Min Range: -1.9086

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1979611 (The Pile)

Max Activating Token Index: 274