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

Dataset: The Pile

Neuron 1720 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: 0.1933. Min Range: -0.1933

Max Act: 0.1933. Min Act: -0.0000

Data Index: 530020 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1849642 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1019704 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1571. Min Act: -0.0000

Data Index: 856023 (The Pile)

Max Activating Token Index: 296

Text #4

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1477. Min Act: -0.0000

Data Index: 531642 (The Pile)

Max Activating Token Index: 796

Text #5

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1326098 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1767630 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1071685 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1579931 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1361. Min Act: -0.0000

Data Index: 274684 (The Pile)

Max Activating Token Index: 778

Text #10

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1938618 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1366. Min Act: -0.0000

Data Index: 348839 (The Pile)

Max Activating Token Index: 551

Text #12

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1455. Min Act: -0.0000

Data Index: 660256 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1415. Min Act: -0.0000

Data Index: 476249 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1773472 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1343. Min Act: -0.0000

Data Index: 342266 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1332. Min Act: -0.0000

Data Index: 451126 (The Pile)

Max Activating Token Index: 683

Text #17

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1097750 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1382. Min Act: -0.0000

Data Index: 829783 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1577424 (The Pile)

Max Activating Token Index: 989