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

Dataset: The Pile

Neuron 3236 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.6190. Min Act: 0.0001

Data Index: 1493913 (The Pile)

Max Activating Token Index: 899

Text #1

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.3801. Min Act: -0.0000

Data Index: 1869664 (The Pile)

Max Activating Token Index: 764

Text #2

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.1287. Min Act: -0.0000

Data Index: 1689478 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.0897. Min Act: -0.0000

Data Index: 218398 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.0527. Min Act: -0.0000

Data Index: 375534 (The Pile)

Max Activating Token Index: 952

Text #5

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1851363 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.9848. Min Act: 0.0000

Data Index: 962294 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.9679. Min Act: -0.0000

Data Index: 631935 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1925656 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.9459. Min Act: 0.0000

Data Index: 1745069 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.0022. Min Act: -0.0000

Data Index: 999413 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.9480. Min Act: 0.0001

Data Index: 128354 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.8662. Min Act: 0.0000

Data Index: 1227727 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1580908 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1074121 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.8069. Min Act: -0.0000

Data Index: 871838 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1077702 (The Pile)

Max Activating Token Index: 276

Text #17

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.9303. Min Act: -0.0000

Data Index: 281337 (The Pile)

Max Activating Token Index: 785

Text #18

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.8875. Min Act: -0.0000

Data Index: 619134 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 1.6190. Min Range: -1.6190

Max Act: 0.8674. Min Act: -0.0000

Data Index: 552500 (The Pile)

Max Activating Token Index: 739