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

Dataset: The Pile

Neuron 4858 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0460. Min Range: -1.0460

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1790531 (The Pile)

Max Activating Token Index: 857

Text #1

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1437669 (The Pile)

Max Activating Token Index: 400

Text #2

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1622598 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1707374 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1870557 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.6960. Min Act: -0.0000

Data Index: 668360 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1403852 (The Pile)

Max Activating Token Index: 204

Text #7

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.6109. Min Act: -0.0000

Data Index: 255139 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.6734. Min Act: 0.0000

Data Index: 376797 (The Pile)

Max Activating Token Index: 305

Text #9

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1034952 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.5549. Min Act: -0.0000

Data Index: 733929 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.6620. Min Act: -0.0000

Data Index: 39586 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1719713 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1484922 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.5914. Min Act: -0.0000

Data Index: 311486 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.6331. Min Act: -0.0000

Data Index: 587213 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1095469 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1735765 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.6015. Min Act: -0.0000

Data Index: 941678 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 1.0460. Min Range: -1.0460

Max Act: 0.6146. Min Act: -0.0000

Data Index: 540165 (The Pile)

Max Activating Token Index: 51