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

Dataset: The Pile

Neuron 318 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.4369. Min Act: -0.0000

Data Index: 1025034 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1856739 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.2594. Min Act: -0.0000

Data Index: 1120503 (The Pile)

Max Activating Token Index: 519

Text #3

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.0216. Min Act: -0.0000

Data Index: 50021 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.0017. Min Act: -0.0000

Data Index: 148107 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1563325 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9232. Min Act: -0.0000

Data Index: 462321 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9385. Min Act: -0.0000

Data Index: 968136 (The Pile)

Max Activating Token Index: 683

Text #8

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9176. Min Act: -0.0000

Data Index: 436770 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1806854 (The Pile)

Max Activating Token Index: 939

Text #10

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1964022 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1234216 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1109160 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1151553 (The Pile)

Max Activating Token Index: 347

Text #14

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1125159 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1038133 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.8633. Min Act: -0.0000

Data Index: 598731 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1309050 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1007477 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.8522. Min Act: -0.0000

Data Index: 209732 (The Pile)

Max Activating Token Index: 753