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

Dataset: The Pile

Neuron 109 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: 1.2342. Min Range: -1.2342

Max Act: 1.2342. Min Act: -0.0000

Data Index: 1399937 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.9887. Min Act: -0.0000

Data Index: 539161 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 1.2342. Min Range: -1.2342

Max Act: 1.1110. Min Act: -0.0000

Data Index: 936833 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8971. Min Act: -0.0000

Data Index: 498150 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8811. Min Act: -0.0000

Data Index: 535859 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1242227 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1848505 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.9050. Min Act: -0.0000

Data Index: 91496 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8619. Min Act: -0.0000

Data Index: 139502 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1369389 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8449. Min Act: -0.0000

Data Index: 661375 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8388. Min Act: -0.0000

Data Index: 166650 (The Pile)

Max Activating Token Index: 233

Text #12

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1889999 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8441. Min Act: -0.0000

Data Index: 205972 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1751204 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.9136. Min Act: -0.0000

Data Index: 557695 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1624562 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1614131 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1206299 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8708. Min Act: -0.0000

Data Index: 170423 (The Pile)

Max Activating Token Index: 693