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

Dataset: The Pile

Neuron 4837 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1365234 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1696482 (The Pile)

Max Activating Token Index: 933

Text #2

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5160. Min Act: -0.0000

Data Index: 778641 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5099. Min Act: -0.0000

Data Index: 844373 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1333321 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1290425 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1099751 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1534258 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4714. Min Act: -0.0000

Data Index: 912120 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1489247 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4223. Min Act: -0.0000

Data Index: 593155 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1063797 (The Pile)

Max Activating Token Index: 574

Text #12

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1235515 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1754750 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4271. Min Act: -0.0000

Data Index: 920481 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4166. Min Act: -0.0000

Data Index: 338615 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4423. Min Act: -0.0000

Data Index: 872899 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4259. Min Act: -0.0000

Data Index: 415149 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4129. Min Act: -0.0000

Data Index: 939918 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4382. Min Act: -0.0000

Data Index: 436380 (The Pile)

Max Activating Token Index: 187