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

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

Neuron 3071 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1517. Min Act: -0.0000

Data Index: 241141 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1554. Min Act: -0.0000

Data Index: 504531 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1562. Min Act: -0.0000

Data Index: 829502 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1480. Min Act: -0.0000

Data Index: 273881 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1587. Min Act: -0.0000

Data Index: 56410 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1476. Min Act: -0.0000

Data Index: 690914 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1376. Min Act: -0.0000

Data Index: 41167 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1432. Min Act: -0.0000

Data Index: 436402 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1460. Min Act: -0.0000

Data Index: 309567 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1430. Min Act: -0.0000

Data Index: 986492 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1474. Min Act: -0.0000

Data Index: 50657 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1346. Min Act: -0.0000

Data Index: 121048 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1343003 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1317. Min Act: -0.0000

Data Index: 619687 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1234814 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1152569 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1356. Min Act: -0.0000

Data Index: 664565 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1346. Min Act: -0.0000

Data Index: 989872 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1385. Min Act: -0.0000

Data Index: 163673 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1241. Min Act: -0.0001

Data Index: 320368 (C4 (Web Text))

Max Activating Token Index: 360