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

Dataset: The Pile

Neuron 319 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3398. Min Act: -0.0000

Data Index: 550846 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3773. Min Act: -0.0000

Data Index: 141553 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2738. Min Act: -0.0000

Data Index: 912337 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3151. Min Act: -0.0000

Data Index: 300515 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1668402 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1557669 (The Pile)

Max Activating Token Index: 625

Text #6

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2722. Min Act: -0.0000

Data Index: 269356 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1187897 (The Pile)

Max Activating Token Index: 503

Text #8

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2750. Min Act: -0.0000

Data Index: 23239 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1822994 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2781. Min Act: -0.0000

Data Index: 456516 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2669. Min Act: -0.0000

Data Index: 24780 (The Pile)

Max Activating Token Index: 99

Text #12

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1946446 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1327324 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1772105 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1873031 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1489250 (The Pile)

Max Activating Token Index: 414

Text #17

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1934169 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2870. Min Act: -0.0000

Data Index: 114734 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2651. Min Act: -0.0000

Data Index: 216044 (The Pile)

Max Activating Token Index: 52