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

Dataset: The Pile

Neuron 3936 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: 0.4324. Min Range: -0.4324

Max Act: 0.4324. Min Act: -0.0000

Data Index: 765812 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.4125. Min Act: 0.0000

Data Index: 130831 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1991618 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3660. Min Act: -0.0000

Data Index: 692155 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3645. Min Act: -0.0000

Data Index: 591174 (The Pile)

Max Activating Token Index: 187

Text #5

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3820. Min Act: -0.0000

Data Index: 395864 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3521. Min Act: 0.0000

Data Index: 1908497 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3427. Min Act: -0.0000

Data Index: 226696 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1523799 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3491. Min Act: -0.0000

Data Index: 875221 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3438. Min Act: 0.0000

Data Index: 541033 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1475052 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3526. Min Act: 0.0000

Data Index: 1410540 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3311. Min Act: 0.0000

Data Index: 550441 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3408. Min Act: -0.0000

Data Index: 361833 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3194. Min Act: 0.0000

Data Index: 1751080 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3278. Min Act: 0.0000

Data Index: 728016 (The Pile)

Max Activating Token Index: 631

Text #17

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1361072 (The Pile)

Max Activating Token Index: 939

Text #18

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3261. Min Act: 0.0000

Data Index: 1805833 (The Pile)

Max Activating Token Index: 587

Text #19

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3183. Min Act: 0.0000

Data Index: 1305560 (The Pile)

Max Activating Token Index: 234