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

Dataset: The Pile

Neuron 1600 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.5001. Min Act: -0.0000

Data Index: 268859 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.4719. Min Act: -0.0000

Data Index: 621094 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1239. Min Act: -0.0000

Data Index: 1633333 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.2990. Min Act: -0.0000

Data Index: 681723 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1359451 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1583889 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.0993. Min Act: -0.0000

Data Index: 725394 (The Pile)

Max Activating Token Index: 949

Text #7

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1668966 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1049. Min Act: -0.0000

Data Index: 61711 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1742. Min Act: -0.0000

Data Index: 983388 (The Pile)

Max Activating Token Index: 294

Text #10

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1322211 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1303. Min Act: -0.0000

Data Index: 1649795 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1114. Min Act: -0.0000

Data Index: 802515 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1192. Min Act: -0.0000

Data Index: 966422 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 1.5001. Min Range: -1.5001

Max Act: 0.9325. Min Act: -0.0000

Data Index: 795759 (The Pile)

Max Activating Token Index: 569

Text #15

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1528981 (The Pile)

Max Activating Token Index: 765

Text #16

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1927077 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 1.5001. Min Range: -1.5001

Max Act: 0.9989. Min Act: -0.0000

Data Index: 209741 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1721449 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.0443. Min Act: -0.0000

Data Index: 486402 (The Pile)

Max Activating Token Index: 712