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

Dataset: The Pile

Neuron 3093 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: 1.5553. Min Range: -1.5553

Max Act: 1.5553. Min Act: -0.0000

Data Index: 614604 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1957334 (The Pile)

Max Activating Token Index: 328

Text #2

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.3251. Min Act: -0.0000

Data Index: 601310 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.4212. Min Act: -0.0000

Data Index: 869314 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.2195. Min Act: -0.0000

Data Index: 1067020 (The Pile)

Max Activating Token Index: 405

Text #5

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.2515. Min Act: -0.0000

Data Index: 982514 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1719301 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1629192 (The Pile)

Max Activating Token Index: 297

Text #8

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1088. Min Act: -0.0000

Data Index: 422316 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.2011. Min Act: -0.0000

Data Index: 983655 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1855. Min Act: -0.0000

Data Index: 440694 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1498. Min Act: -0.0000

Data Index: 775656 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1492029 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1324401 (The Pile)

Max Activating Token Index: 116

Text #14

Max Range: 1.5553. Min Range: -1.5553

Max Act: 0.9924. Min Act: -0.0000

Data Index: 354557 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1891638 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.0399. Min Act: -0.0000

Data Index: 1076630 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 1.5553. Min Range: -1.5553

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1237603 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.0879. Min Act: -0.0000

Data Index: 224804 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.0874. Min Act: -0.0000

Data Index: 375410 (The Pile)

Max Activating Token Index: 571