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

Dataset: The Pile

Neuron 3625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.2527. Min Act: -0.0000

Data Index: 288413 (The Pile)

Max Activating Token Index: 14

Text #1

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.8979. Min Act: -0.0000

Data Index: 963318 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.9399. Min Act: -0.0000

Data Index: 1518502 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.8097. Min Act: -0.0000

Data Index: 1697090 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.9270. Min Act: -0.0000

Data Index: 587550 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0469. Min Act: -0.0000

Data Index: 1726846 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.9963. Min Act: -0.0000

Data Index: 1596019 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.8347. Min Act: -0.0000

Data Index: 81783 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.8384. Min Act: -0.0000

Data Index: 1303031 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1301. Min Act: -0.0000

Data Index: 1036296 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.9253. Min Act: -0.0000

Data Index: 1314805 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.6449. Min Act: -0.0000

Data Index: 222082 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.9103. Min Act: -0.0000

Data Index: 981706 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.2192. Min Act: -0.0000

Data Index: 1593865 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0448. Min Act: -0.0000

Data Index: 990142 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.6026. Min Act: -0.0000

Data Index: 585312 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.6030. Min Act: -0.0000

Data Index: 1212609 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.7374. Min Act: -0.0000

Data Index: 927176 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0183. Min Act: -0.0000

Data Index: 232871 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 3.2527. Min Range: -3.2527

Max Act: 2.9653. Min Act: -0.0000

Data Index: 1521457 (The Pile)

Max Activating Token Index: 22