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

Dataset: The Pile

Neuron 3217 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.8240. Min Act: -0.0000

Data Index: 1036143 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.4334. Min Act: -0.0000

Data Index: 1051833 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.9707. Min Act: -0.0000

Data Index: 646089 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.3832. Min Act: -0.0000

Data Index: 1741787 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.4001. Min Act: -0.0000

Data Index: 895124 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.4476. Min Act: -0.0000

Data Index: 921440 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 7.9707. Min Range: -7.9707

Max Act: 6.8726. Min Act: -0.0000

Data Index: 1866337 (The Pile)

Max Activating Token Index: 401

Text #7

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.2102. Min Act: -0.0000

Data Index: 1186284 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.3020. Min Act: -0.0000

Data Index: 1207904 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 7.9707. Min Range: -7.9707

Max Act: 6.7675. Min Act: -0.0000

Data Index: 273860 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.3159. Min Act: -0.0000

Data Index: 1029977 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.1097. Min Act: -0.0000

Data Index: 1949382 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.2632. Min Act: -0.0000

Data Index: 32062 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.2496. Min Act: -0.0000

Data Index: 1339546 (The Pile)

Max Activating Token Index: 373

Text #14

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.0403. Min Act: -0.0000

Data Index: 692635 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.3946. Min Act: -0.0000

Data Index: 841290 (The Pile)

Max Activating Token Index: 31

Text #16

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.0485. Min Act: -0.0000

Data Index: 1026914 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.0131. Min Act: -0.0000

Data Index: 194142 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.2179. Min Act: -0.0000

Data Index: 587710 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 7.9707. Min Range: -7.9707

Max Act: 6.8067. Min Act: -0.0000

Data Index: 1382290 (The Pile)

Max Activating Token Index: 140