Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2074 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1637. Min Act: -0.0001

Data Index: 442171 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1192770 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1604. Min Act: -0.0001

Data Index: 65611 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1611. Min Act: -0.0001

Data Index: 107577 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1176434 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1593. Min Act: -0.0001

Data Index: 644094 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1203031 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1128863 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1025832 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1112319 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1488. Min Act: -0.0001

Data Index: 455095 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1429. Min Act: -0.0001

Data Index: 521742 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1387. Min Act: -0.0001

Data Index: 701728 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1366. Min Act: -0.0001

Data Index: 788576 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1275830 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1465. Min Act: -0.0001

Data Index: 649009 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1399. Min Act: -0.0001

Data Index: 844654 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1393486 (Python Code)

Max Activating Token Index: 336

Text #18

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1330. Min Act: -0.0001

Data Index: 469574 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1318. Min Act: -0.0001

Data Index: 644517 (C4 (Web Text))

Max Activating Token Index: 98