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

Dataset: The Pile

Neuron 3459 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: 0.9737. Min Range: -0.9737

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1081119 (The Pile)

Max Activating Token Index: 659

Text #1

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.9556. Min Act: -0.0000

Data Index: 1174870 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.9013. Min Act: -0.0000

Data Index: 315683 (The Pile)

Max Activating Token Index: 521

Text #3

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.8253. Min Act: -0.0000

Data Index: 249903 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.8088. Min Act: -0.0000

Data Index: 654041 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1390640 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.8241. Min Act: -0.0000

Data Index: 259184 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1723312 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7361. Min Act: -0.0000

Data Index: 990341 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7232. Min Act: -0.0000

Data Index: 991567 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1262229 (The Pile)

Max Activating Token Index: 20

Text #11

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1930697 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.6872. Min Act: -0.0000

Data Index: 558212 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7301. Min Act: -0.0000

Data Index: 921155 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.6765. Min Act: -0.0000

Data Index: 988890 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.6642. Min Act: -0.0000

Data Index: 374126 (The Pile)

Max Activating Token Index: 20

Text #16

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.6535. Min Act: -0.0000

Data Index: 517791 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1100289 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.6703. Min Act: -0.0000

Data Index: 140025 (The Pile)

Max Activating Token Index: 498

Text #19

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1117184 (The Pile)

Max Activating Token Index: 370