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

Dataset: The Pile

Neuron 4393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1072728 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0640. Min Act: -0.0000

Data Index: 778218 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.2256. Min Act: -0.0000

Data Index: 1835063 (The Pile)

Max Activating Token Index: 871

Text #3

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1200784 (The Pile)

Max Activating Token Index: 68

Text #4

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0392. Min Act: -0.0000

Data Index: 387002 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1850171 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1476911 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0336. Min Act: -0.0000

Data Index: 311211 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1174533 (The Pile)

Max Activating Token Index: 231

Text #9

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1949740 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1477243 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1021365 (The Pile)

Max Activating Token Index: 275

Text #12

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1134315 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9421. Min Act: -0.0000

Data Index: 622762 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9730. Min Act: -0.0000

Data Index: 160709 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9104. Min Act: -0.0000

Data Index: 750238 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1748631 (The Pile)

Max Activating Token Index: 211

Text #17

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8717. Min Act: -0.0000

Data Index: 1912678 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1197510 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1042895 (The Pile)

Max Activating Token Index: 556