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

Dataset: The Pile

Neuron 3566 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1496. Min Range: -1.1496

Max Act: 1.1496. Min Act: -0.0000

Data Index: 149810 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.1496. Min Range: -1.1496

Max Act: 1.0969. Min Act: -0.0000

Data Index: 158656 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 1.1496. Min Range: -1.1496

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1913284 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 1.1496. Min Range: -1.1496

Max Act: 1.0208. Min Act: -0.0000

Data Index: 508165 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1298165 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 1.1496. Min Range: -1.1496

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1130818 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 1.1496. Min Range: -1.1496

Max Act: 1.0692. Min Act: -0.0000

Data Index: 556210 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.9108. Min Act: -0.0000

Data Index: 723168 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1598279 (The Pile)

Max Activating Token Index: 508

Text #9

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.9768. Min Act: -0.0000

Data Index: 619043 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1488643 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 1.1496. Min Range: -1.1496

Max Act: 1.0055. Min Act: -0.0000

Data Index: 103053 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.9280. Min Act: -0.0000

Data Index: 253258 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1299183 (The Pile)

Max Activating Token Index: 53

Text #14

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.9980. Min Act: -0.0000

Data Index: 988178 (The Pile)

Max Activating Token Index: 829

Text #15

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.9217. Min Act: -0.0000

Data Index: 299895 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.8375. Min Act: -0.0000

Data Index: 307927 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.8373. Min Act: -0.0000

Data Index: 844708 (The Pile)

Max Activating Token Index: 128

Text #18

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1425175 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 1.1496. Min Range: -1.1496

Max Act: 0.8442. Min Act: -0.0000

Data Index: 898982 (The Pile)

Max Activating Token Index: 362