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

Dataset: The Pile

Neuron 930 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.7066. Min Act: -0.0000

Data Index: 1947195 (The Pile)

Max Activating Token Index: 409

Text #1

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.7346. Min Act: -0.0000

Data Index: 1719213 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.6515. Min Act: -0.0000

Data Index: 802328 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.4903. Min Act: -0.0000

Data Index: 722128 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.5449. Min Act: -0.0000

Data Index: 449267 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.4316. Min Act: -0.0000

Data Index: 585666 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.5691. Min Act: -0.0000

Data Index: 1427096 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1902581 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3160. Min Act: -0.0000

Data Index: 228822 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3860. Min Act: -0.0000

Data Index: 1514501 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.4229. Min Act: -0.0000

Data Index: 509648 (The Pile)

Max Activating Token Index: 367

Text #11

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3050. Min Act: -0.0000

Data Index: 560343 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.4359. Min Act: -0.0000

Data Index: 383397 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2696. Min Act: -0.0000

Data Index: 1299783 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2417. Min Act: -0.0000

Data Index: 1994171 (The Pile)

Max Activating Token Index: 799

Text #15

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3973. Min Act: -0.0000

Data Index: 1420515 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3694. Min Act: -0.0000

Data Index: 1977507 (The Pile)

Max Activating Token Index: 553

Text #17

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3144. Min Act: -0.0000

Data Index: 1896286 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2860. Min Act: -0.0000

Data Index: 449233 (The Pile)

Max Activating Token Index: 171

Text #19

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1780488 (The Pile)

Max Activating Token Index: 64