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

Dataset: The Pile

Neuron 371 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1633670 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 1.0136. Min Range: -1.0136

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1626231 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 1.0136. Min Range: -1.0136

Max Act: 1.0111. Min Act: -0.0000

Data Index: 940816 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1278021 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8546. Min Act: -0.0000

Data Index: 242507 (The Pile)

Max Activating Token Index: 952

Text #5

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8732. Min Act: 0.0000

Data Index: 614952 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7726. Min Act: -0.0000

Data Index: 537467 (The Pile)

Max Activating Token Index: 897

Text #7

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1842848 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7709. Min Act: -0.0000

Data Index: 605967 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7611. Min Act: -0.0000

Data Index: 287415 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7953. Min Act: -0.0000

Data Index: 770571 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1665814 (The Pile)

Max Activating Token Index: 940

Text #12

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7735. Min Act: -0.0000

Data Index: 577584 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1857863 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1923173 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.6810. Min Act: -0.0000

Data Index: 284624 (The Pile)

Max Activating Token Index: 377

Text #16

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1140589 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.6705. Min Act: 0.0000

Data Index: 1474484 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1258875 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1318196 (The Pile)

Max Activating Token Index: 89