Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1663. Min Act: -0.0001

Data Index: 1278234 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1464. Min Act: -0.0000

Data Index: 972708 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1603. Min Act: -0.0001

Data Index: 712454 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1327. Min Act: -0.0001

Data Index: 988672 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1296442 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1372. Min Act: -0.0001

Data Index: 738246 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1469. Min Act: -0.0001

Data Index: 371265 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1290474 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1411. Min Act: -0.0001

Data Index: 279347 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1336275 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1430. Min Act: -0.0001

Data Index: 197767 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1307955 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1200753 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1383. Min Act: -0.0000

Data Index: 634209 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1225. Min Act: -0.0001

Data Index: 453450 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1370. Min Act: -0.0001

Data Index: 457518 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1417. Min Act: -0.0001

Data Index: 885242 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1363. Min Act: -0.0001

Data Index: 768731 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1180. Min Act: -0.0001

Data Index: 6143 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1356. Min Act: -0.0001

Data Index: 642377 (C4 (Web Text))

Max Activating Token Index: 448