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

Dataset: The Pile

Neuron 3813 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: 1.4670. Min Range: -1.4670

Max Act: 1.4670. Min Act: -0.0000

Data Index: 1631704 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.4613. Min Act: -0.0000

Data Index: 1746096 (The Pile)

Max Activating Token Index: 342

Text #2

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.2273. Min Act: -0.0000

Data Index: 404968 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9825. Min Act: -0.0000

Data Index: 113076 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1932730 (The Pile)

Max Activating Token Index: 45

Text #5

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1330397 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9194. Min Act: -0.0000

Data Index: 213432 (The Pile)

Max Activating Token Index: 566

Text #7

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9290. Min Act: -0.0000

Data Index: 285511 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9964. Min Act: -0.0000

Data Index: 861334 (The Pile)

Max Activating Token Index: 281

Text #9

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1921034 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1558759 (The Pile)

Max Activating Token Index: 816

Text #11

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1639313 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1909316 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8489. Min Act: -0.0000

Data Index: 245881 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1286957 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8726. Min Act: -0.0000

Data Index: 629919 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1227795 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1038370 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8858. Min Act: -0.0000

Data Index: 110853 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9738. Min Act: -0.0000

Data Index: 1445565 (The Pile)

Max Activating Token Index: 700