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

Dataset: The Pile

Neuron 3613 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: 3.8323. Min Range: -3.8323

Max Act: 3.8323. Min Act: -0.0000

Data Index: 314930 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.6408. Min Act: -0.0000

Data Index: 53783 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.3803. Min Act: -0.0000

Data Index: 1394968 (The Pile)

Max Activating Token Index: 903

Text #3

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.2658. Min Act: -0.0000

Data Index: 1866253 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.2079. Min Act: -0.0000

Data Index: 1574221 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.1495. Min Act: -0.0000

Data Index: 1135483 (The Pile)

Max Activating Token Index: 597

Text #6

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.1269. Min Act: -0.0000

Data Index: 1189766 (The Pile)

Max Activating Token Index: 243

Text #7

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.1215. Min Act: -0.0000

Data Index: 79077 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.2149. Min Act: -0.0000

Data Index: 1910358 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 3.8323. Min Range: -3.8323

Max Act: 2.9366. Min Act: -0.0000

Data Index: 1051382 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.1992. Min Act: -0.0000

Data Index: 1838615 (The Pile)

Max Activating Token Index: 295

Text #11

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.1449. Min Act: -0.0000

Data Index: 1039742 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 3.8323. Min Range: -3.8323

Max Act: 2.9944. Min Act: -0.0000

Data Index: 107876 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 3.8323. Min Range: -3.8323

Max Act: 2.9429. Min Act: -0.0000

Data Index: 1507040 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.0663. Min Act: -0.0000

Data Index: 975515 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 3.8323. Min Range: -3.8323

Max Act: 2.9241. Min Act: -0.0000

Data Index: 1883664 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 3.8323. Min Range: -3.8323

Max Act: 2.7627. Min Act: -0.0000

Data Index: 808643 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 3.8323. Min Range: -3.8323

Max Act: 2.8922. Min Act: -0.0000

Data Index: 1354134 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 3.8323. Min Range: -3.8323

Max Act: 3.0181. Min Act: -0.0000

Data Index: 1124071 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 3.8323. Min Range: -3.8323

Max Act: 2.8881. Min Act: -0.0000

Data Index: 1370888 (The Pile)

Max Activating Token Index: 64