Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2413 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.9846. Min Act: -0.0000

Data Index: 1151449 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.4855. Min Act: -0.0000

Data Index: 1099425 (The Pile)

Max Activating Token Index: 909

Text #2

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.9619. Min Act: -0.0000

Data Index: 1796104 (The Pile)

Max Activating Token Index: 926

Text #3

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.4181. Min Act: -0.0000

Data Index: 1831808 (The Pile)

Max Activating Token Index: 589

Text #4

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1474870 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.3604. Min Act: -0.0000

Data Index: 407125 (The Pile)

Max Activating Token Index: 771

Text #6

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.6023. Min Act: -0.0000

Data Index: 808706 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.2056. Min Act: -0.0000

Data Index: 1451450 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.1790. Min Act: -0.0000

Data Index: 933946 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1908143 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.1501. Min Act: -0.0000

Data Index: 779006 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1428724 (The Pile)

Max Activating Token Index: 358

Text #12

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.2878. Min Act: -0.0000

Data Index: 522356 (The Pile)

Max Activating Token Index: 916

Text #13

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.9538. Min Act: -0.0000

Data Index: 771639 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1069084 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.0828. Min Act: -0.0000

Data Index: 1919906 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1144058 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1647486 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1596338 (The Pile)

Max Activating Token Index: 403

Text #19

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.1101. Min Act: -0.0000

Data Index: 151078 (The Pile)

Max Activating Token Index: 753