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

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

Neuron 6007 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1863. Min Act: -0.0000

Data Index: 830350 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1738. Min Act: -0.0001

Data Index: 794389 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1151039 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1499702 (Python Code)

Max Activating Token Index: 647

Text #4

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1617. Min Act: -0.0001

Data Index: 579580 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1213836 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1116854 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1457. Min Act: -0.0001

Data Index: 31155 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1309. Min Act: -0.0001

Data Index: 819982 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1394. Min Act: -0.0001

Data Index: 55759 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1412. Min Act: -0.0001

Data Index: 126876 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1235880 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1407657 (Python Code)

Max Activating Token Index: 192

Text #13

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1325. Min Act: -0.0001

Data Index: 510353 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1271. Min Act: -0.0001

Data Index: 970773 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1307. Min Act: -0.0001

Data Index: 376820 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1274. Min Act: -0.0000

Data Index: 842489 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1273. Min Act: -0.0001

Data Index: 377090 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1243. Min Act: -0.0001

Data Index: 307112 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1493534 (Python Code)

Max Activating Token Index: 965