Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4832 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1802. Min Act: -0.0000

Data Index: 758240 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1486. Min Act: -0.0000

Data Index: 526000 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1232328 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1416. Min Act: -0.0000

Data Index: 669094 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1475. Min Act: -0.0000

Data Index: 823168 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1399. Min Act: -0.0000

Data Index: 725440 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1336429 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1355. Min Act: -0.0000

Data Index: 745530 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1469. Min Act: -0.0000

Data Index: 762917 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1255. Min Act: -0.0000

Data Index: 614900 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1277. Min Act: -0.0000

Data Index: 611955 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1183593 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1203. Min Act: -0.0000

Data Index: 805631 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1200. Min Act: -0.0000

Data Index: 295882 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1260. Min Act: -0.0000

Data Index: 872112 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1151. Min Act: -0.0000

Data Index: 370125 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1044. Min Act: -0.0000

Data Index: 512566 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1085. Min Act: -0.0000

Data Index: 606306 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1127. Min Act: -0.0000

Data Index: 399675 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1274148 (C4 (Web Text))

Max Activating Token Index: 951