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

Dataset: The Pile

Neuron 3253 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1444. Min Range: -1.1444

Max Act: 1.1444. Min Act: -0.0000

Data Index: 1152152 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.8914. Min Act: -0.0000

Data Index: 376550 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1161827 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.8901. Min Act: -0.0000

Data Index: 673703 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.8335. Min Act: -0.0000

Data Index: 336000 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1455163 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.7604. Min Act: -0.0000

Data Index: 589291 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1786715 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.7203. Min Act: -0.0000

Data Index: 71102 (The Pile)

Max Activating Token Index: 805

Text #9

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.7016. Min Act: -0.0000

Data Index: 663509 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.7265. Min Act: -0.0000

Data Index: 180700 (The Pile)

Max Activating Token Index: 82

Text #11

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.6367. Min Act: -0.0000

Data Index: 920750 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1432103 (The Pile)

Max Activating Token Index: 391

Text #13

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.7076. Min Act: -0.0000

Data Index: 105107 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.5969. Min Act: -0.0001

Data Index: 1310797 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.6424. Min Act: 0.0000

Data Index: 104070 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1443596 (The Pile)

Max Activating Token Index: 274

Text #17

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.6627. Min Act: 0.0000

Data Index: 1630631 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.6348. Min Act: -0.0000

Data Index: 843291 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.6260. Min Act: -0.0000

Data Index: 314697 (The Pile)

Max Activating Token Index: 979