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

Dataset: The Pile

Neuron 2131 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: 4.1137. Min Range: -4.1137

Max Act: 3.9733. Min Act: -0.0000

Data Index: 1421745 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 4.1137. Min Range: -4.1137

Max Act: 4.1137. Min Act: -0.0000

Data Index: 924243 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.4037. Min Act: -0.0000

Data Index: 88597 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.3871. Min Act: -0.0000

Data Index: 84498 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.4041. Min Act: -0.0000

Data Index: 866660 (The Pile)

Max Activating Token Index: 463

Text #5

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.5302. Min Act: -0.0000

Data Index: 1546903 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.5011. Min Act: -0.0000

Data Index: 1767112 (The Pile)

Max Activating Token Index: 228

Text #7

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.1523. Min Act: 0.0000

Data Index: 1960743 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.4176. Min Act: -0.0000

Data Index: 1297302 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.1828. Min Act: 0.0000

Data Index: 263641 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 4.1137. Min Range: -4.1137

Max Act: 2.9924. Min Act: -0.0000

Data Index: 1656682 (The Pile)

Max Activating Token Index: 5

Text #11

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.1515. Min Act: -0.0000

Data Index: 1116547 (The Pile)

Max Activating Token Index: 596

Text #12

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.0965. Min Act: -0.0000

Data Index: 445319 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.2142. Min Act: -0.0000

Data Index: 1436485 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.0377. Min Act: -0.0000

Data Index: 1786152 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.0254. Min Act: -0.0000

Data Index: 1338130 (The Pile)

Max Activating Token Index: 472

Text #16

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.1870. Min Act: -0.0000

Data Index: 588626 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 4.1137. Min Range: -4.1137

Max Act: 3.0162. Min Act: -0.0000

Data Index: 86322 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 4.1137. Min Range: -4.1137

Max Act: 2.9703. Min Act: -0.0000

Data Index: 375860 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 4.1137. Min Range: -4.1137

Max Act: 2.9637. Min Act: -0.0000

Data Index: 865277 (The Pile)

Max Activating Token Index: 252