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

Dataset: The Pile

Neuron 4025 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1488139 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1264590 (The Pile)

Max Activating Token Index: 765

Text #2

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5876. Min Act: -0.0000

Data Index: 94323 (The Pile)

Max Activating Token Index: 865

Text #3

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5201. Min Act: -0.0000

Data Index: 125885 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5292. Min Act: 0.0001

Data Index: 729725 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1943921 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1216674 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5671. Min Act: -0.0000

Data Index: 558569 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5823. Min Act: 0.0000

Data Index: 1223630 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5422. Min Act: -0.0000

Data Index: 74866 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1190891 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1888628 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1462525 (The Pile)

Max Activating Token Index: 993

Text #13

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5313. Min Act: -0.0000

Data Index: 702553 (The Pile)

Max Activating Token Index: 301

Text #14

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4986. Min Act: -0.0000

Data Index: 466159 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1539994 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1069160 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1268804 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4897. Min Act: -0.0000

Data Index: 783638 (The Pile)

Max Activating Token Index: 492

Text #19

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5148. Min Act: -0.0000

Data Index: 975269 (The Pile)

Max Activating Token Index: 887