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

Dataset: The Pile

Neuron 102 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: 0.6883. Min Range: -0.6883

Max Act: 0.6883. Min Act: 0.0000

Data Index: 934784 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6706. Min Act: -0.0000

Data Index: 224478 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6591. Min Act: -0.0000

Data Index: 670122 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6502. Min Act: 0.0001

Data Index: 1441419 (The Pile)

Max Activating Token Index: 563

Text #4

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1236365 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6101. Min Act: -0.0000

Data Index: 467757 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1956001 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1600586 (The Pile)

Max Activating Token Index: 878

Text #8

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6222. Min Act: -0.0000

Data Index: 813372 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6064. Min Act: -0.0000

Data Index: 405369 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5995. Min Act: -0.0000

Data Index: 991475 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1378650 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5959. Min Act: -0.0000

Data Index: 530261 (The Pile)

Max Activating Token Index: 350

Text #13

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6065. Min Act: -0.0000

Data Index: 387428 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5793. Min Act: -0.0000

Data Index: 581474 (The Pile)

Max Activating Token Index: 448

Text #15

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1397216 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1876597 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1378401 (The Pile)

Max Activating Token Index: 364

Text #18

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5684. Min Act: -0.0000

Data Index: 142871 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5971. Min Act: -0.0000

Data Index: 876280 (The Pile)

Max Activating Token Index: 195