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

Dataset: The Pile

Neuron 4945 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: 0.7105. Min Range: -0.7105

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1393463 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1986831 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4793. Min Act: 0.0000

Data Index: 108978 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1690469 (The Pile)

Max Activating Token Index: 782

Text #4

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1511646 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4650. Min Act: -0.0000

Data Index: 746652 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4376. Min Act: -0.0000

Data Index: 458185 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1790130 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1988758 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4242. Min Act: -0.0000

Data Index: 802781 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1488258 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4308. Min Act: -0.0000

Data Index: 330714 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4424. Min Act: -0.0000

Data Index: 299785 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1640526 (The Pile)

Max Activating Token Index: 999

Text #14

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1964828 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1142356 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1224389 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1543627 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4127. Min Act: -0.0000

Data Index: 911101 (The Pile)

Max Activating Token Index: 909

Text #19

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1734231 (The Pile)

Max Activating Token Index: 137