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

Dataset: The Pile

Neuron 1140 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: 1.9644. Min Range: -1.9644

Max Act: 1.9644. Min Act: -0.0000

Data Index: 836706 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.9611. Min Act: -0.0000

Data Index: 320178 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8949. Min Act: -0.0000

Data Index: 1592997 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8397. Min Act: -0.0000

Data Index: 1950513 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8452. Min Act: -0.0000

Data Index: 1190626 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.7179. Min Act: -0.0000

Data Index: 450215 (The Pile)

Max Activating Token Index: 873

Text #6

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.7757. Min Act: -0.0000

Data Index: 803806 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5692. Min Act: -0.0000

Data Index: 1664674 (The Pile)

Max Activating Token Index: 845

Text #8

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.6909. Min Act: -0.0000

Data Index: 20146 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.6671. Min Act: -0.0000

Data Index: 786106 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.6748. Min Act: -0.0000

Data Index: 1772875 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.6341. Min Act: -0.0000

Data Index: 1237124 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5839. Min Act: -0.0000

Data Index: 1645972 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1175099 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5732. Min Act: -0.0000

Data Index: 1140678 (The Pile)

Max Activating Token Index: 994

Text #15

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1426445 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.6335. Min Act: -0.0000

Data Index: 1489095 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5294. Min Act: -0.0000

Data Index: 1444233 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5925. Min Act: -0.0000

Data Index: 1093074 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1470243 (The Pile)

Max Activating Token Index: 324