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

Dataset: The Pile

Neuron 4817 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.6367. Min Act: -0.0000

Data Index: 1301571 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5712. Min Act: -0.0000

Data Index: 1140907 (The Pile)

Max Activating Token Index: 149

Text #2

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5333. Min Act: -0.0000

Data Index: 1762839 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5071. Min Act: -0.0000

Data Index: 1875283 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4985. Min Act: -0.0000

Data Index: 1098673 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4200. Min Act: -0.0000

Data Index: 89641 (The Pile)

Max Activating Token Index: 291

Text #6

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4858. Min Act: -0.0000

Data Index: 852850 (The Pile)

Max Activating Token Index: 929

Text #7

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4466. Min Act: -0.0000

Data Index: 1621967 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3350. Min Act: -0.0000

Data Index: 865883 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3962. Min Act: -0.0000

Data Index: 230363 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4812. Min Act: -0.0000

Data Index: 1919095 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3694. Min Act: -0.0000

Data Index: 227648 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3575. Min Act: -0.0000

Data Index: 1970208 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.2312. Min Act: -0.0000

Data Index: 540158 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4116. Min Act: -0.0000

Data Index: 1212520 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3357. Min Act: -0.0000

Data Index: 395343 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3226. Min Act: -0.0000

Data Index: 1405246 (The Pile)

Max Activating Token Index: 1004

Text #17

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3306. Min Act: -0.0000

Data Index: 481310 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.2519. Min Act: -0.0000

Data Index: 137136 (The Pile)

Max Activating Token Index: 278

Text #19

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3096. Min Act: -0.0000

Data Index: 1187028 (The Pile)

Max Activating Token Index: 733