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

Dataset: The Pile

Neuron 936 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: 1.8130. Min Range: -1.8130

Max Act: 1.8130. Min Act: 0.0000

Data Index: 554332 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.5844. Min Act: -0.0000

Data Index: 1426580 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1658467 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.4961. Min Act: -0.0000

Data Index: 1053416 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1467231 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.4394. Min Act: -0.0000

Data Index: 1891032 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.3338. Min Act: -0.0000

Data Index: 1488446 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.2750. Min Act: -0.0000

Data Index: 16627 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.3105. Min Act: 0.0000

Data Index: 1623305 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.2754. Min Act: -0.0000

Data Index: 42300 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.1879. Min Act: -0.0000

Data Index: 493536 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.1900. Min Act: -0.0000

Data Index: 121917 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.2271. Min Act: -0.0000

Data Index: 1588408 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.1405. Min Act: -0.0000

Data Index: 1462244 (The Pile)

Max Activating Token Index: 114

Text #14

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.2057. Min Act: -0.0000

Data Index: 1894785 (The Pile)

Max Activating Token Index: 850

Text #15

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.1238. Min Act: -0.0000

Data Index: 1078421 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1187766 (The Pile)

Max Activating Token Index: 440

Text #17

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.0941. Min Act: -0.0000

Data Index: 712102 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.1491. Min Act: -0.0000

Data Index: 557639 (The Pile)

Max Activating Token Index: 704

Text #19

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.0895. Min Act: -0.0000

Data Index: 245037 (The Pile)

Max Activating Token Index: 544