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

Dataset: The Pile

Neuron 2363 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.8249. Min Act: -0.0000

Data Index: 269133 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7164. Min Act: -0.0000

Data Index: 388507 (The Pile)

Max Activating Token Index: 776

Text #2

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1776097 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6559. Min Act: -0.0000

Data Index: 17537 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6001. Min Act: -0.0000

Data Index: 593408 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5745. Min Act: -0.0000

Data Index: 708733 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5877. Min Act: -0.0000

Data Index: 272516 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5609. Min Act: -0.0000

Data Index: 790800 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5848. Min Act: -0.0000

Data Index: 878228 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5469. Min Act: -0.0000

Data Index: 838972 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1299855 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1331926 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1116649 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1176684 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1816042 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1197679 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.4908. Min Act: -0.0000

Data Index: 668090 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5910. Min Act: -0.0000

Data Index: 681990 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5323. Min Act: -0.0000

Data Index: 223840 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5421. Min Act: -0.0000

Data Index: 996945 (The Pile)

Max Activating Token Index: 88