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

Dataset: The Pile

Neuron 3545 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0453. Min Range: -1.0453

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1609945 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9900. Min Act: -0.0000

Data Index: 322677 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 1.0453. Min Range: -1.0453

Max Act: 1.0174. Min Act: -0.0000

Data Index: 211587 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9886. Min Act: -0.0000

Data Index: 1444563 (The Pile)

Max Activating Token Index: 646

Text #4

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1397679 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1791636 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1901460 (The Pile)

Max Activating Token Index: 22

Text #7

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9147. Min Act: -0.0000

Data Index: 969158 (The Pile)

Max Activating Token Index: 28

Text #8

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1549759 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1679584 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1179909 (The Pile)

Max Activating Token Index: 880

Text #11

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1161402 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9363. Min Act: -0.0000

Data Index: 505069 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1934784 (The Pile)

Max Activating Token Index: 749

Text #14

Max Range: 1.0453. Min Range: -1.0453

Max Act: 1.0051. Min Act: -0.0000

Data Index: 156241 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9303. Min Act: -0.0000

Data Index: 347775 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1277170 (The Pile)

Max Activating Token Index: 25

Text #17

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9303. Min Act: -0.0000

Data Index: 574571 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9052. Min Act: -0.0000

Data Index: 1953145 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9233. Min Act: -0.0000

Data Index: 119565 (The Pile)

Max Activating Token Index: 22