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

Dataset: The Pile

Neuron 2255 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.2234. Min Act: -0.0000

Data Index: 17493 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.1097. Min Act: -0.0000

Data Index: 1260265 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.0282. Min Act: -0.0000

Data Index: 215403 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1790766 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1029801 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1948311 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9763. Min Act: -0.0000

Data Index: 934433 (The Pile)

Max Activating Token Index: 625

Text #7

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1675200 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9044. Min Act: -0.0000

Data Index: 913836 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1700775 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7819. Min Act: -0.0000

Data Index: 482727 (The Pile)

Max Activating Token Index: 581

Text #11

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1622764 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8802. Min Act: -0.0000

Data Index: 56616 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7846. Min Act: -0.0000

Data Index: 629500 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1754553 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1799022 (The Pile)

Max Activating Token Index: 644

Text #16

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8146. Min Act: -0.0000

Data Index: 694923 (The Pile)

Max Activating Token Index: 1004

Text #17

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1099482 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8040. Min Act: -0.0000

Data Index: 897134 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7684. Min Act: -0.0000

Data Index: 565989 (The Pile)

Max Activating Token Index: 820