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

Dataset: The Pile

Neuron 1784 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0650. Min Range: -1.0650

Max Act: 1.0650. Min Act: -0.0000

Data Index: 128611 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 1.0650. Min Range: -1.0650

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1294110 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 1.0650. Min Range: -1.0650

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1923303 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9310. Min Act: 0.0000

Data Index: 810003 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8214. Min Act: 0.0000

Data Index: 1041970 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7429. Min Act: -0.0000

Data Index: 8040 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1113886 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8416. Min Act: -0.0000

Data Index: 988813 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8151. Min Act: -0.0000

Data Index: 522287 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7639. Min Act: 0.0000

Data Index: 611690 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1865777 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1790972 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7530. Min Act: -0.0000

Data Index: 65858 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7437. Min Act: -0.0000

Data Index: 681511 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1776845 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.6920. Min Act: -0.0000

Data Index: 694351 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7902. Min Act: 0.0000

Data Index: 1476728 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7024. Min Act: 0.0000

Data Index: 1540739 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7293. Min Act: -0.0000

Data Index: 600036 (The Pile)

Max Activating Token Index: 881

Text #19

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7278. Min Act: -0.0000

Data Index: 165340 (The Pile)

Max Activating Token Index: 894