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

Dataset: The Pile

Neuron 450 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: 0.2444. Min Range: -0.2444

Max Act: 0.2444. Min Act: -0.0000

Data Index: 778098 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1704. Min Act: -0.0000

Data Index: 571667 (The Pile)

Max Activating Token Index: 850

Text #2

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1162408 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1501. Min Act: -0.0000

Data Index: 295075 (The Pile)

Max Activating Token Index: 839

Text #4

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1418102 (The Pile)

Max Activating Token Index: 583

Text #5

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1363281 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1442. Min Act: -0.0000

Data Index: 675427 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1793706 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1595095 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1234. Min Act: -0.0000

Data Index: 387717 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1222. Min Act: -0.0000

Data Index: 936173 (The Pile)

Max Activating Token Index: 799

Text #11

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1324. Min Act: -0.0000

Data Index: 9507 (The Pile)

Max Activating Token Index: 727

Text #12

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1825192 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1088367 (The Pile)

Max Activating Token Index: 870

Text #14

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1279. Min Act: -0.0000

Data Index: 819615 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1186. Min Act: -0.0000

Data Index: 300479 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1127967 (The Pile)

Max Activating Token Index: 788

Text #17

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1529298 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1652090 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1464521 (The Pile)

Max Activating Token Index: 465