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

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

Neuron 2439 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: 2.1364. Min Range: -2.1364

Max Act: 2.1364. Min Act: -0.0000

Data Index: 535897 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.4711. Min Act: -0.0000

Data Index: 466582 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.3506. Min Act: -0.0000

Data Index: 146532 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.2423. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1867. Min Act: -0.0000

Data Index: 715432 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.0436. Min Act: -0.0000

Data Index: 784270 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1821. Min Act: -0.0000

Data Index: 970494 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1896. Min Act: -0.0000

Data Index: 298700 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1574. Min Act: -0.0000

Data Index: 863401 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1711. Min Act: -0.0000

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1989. Min Act: -0.0000

Data Index: 451447 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1479954 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1092725 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1563. Min Act: -0.0000

Data Index: 942332 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 2.1364. Min Range: -2.1364

Max Act: 0.9493. Min Act: -0.0000

Data Index: 802064 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1210194 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.1655. Min Act: -0.0000

Data Index: 1218088 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1404102 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 2.1364. Min Range: -2.1364

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1344888 (C4 (Web Text))

Max Activating Token Index: 754