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

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

Neuron 1265 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: 0.1886. Min Range: -0.1886

Max Act: 0.1886. Min Act: -0.0001

Data Index: 992422 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1709. Min Act: -0.0001

Data Index: 117050 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1355152 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1703. Min Act: -0.0001

Data Index: 749653 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1615. Min Act: -0.0001

Data Index: 95584 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1606. Min Act: -0.0001

Data Index: 642322 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1531. Min Act: -0.0001

Data Index: 591391 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1630. Min Act: -0.0001

Data Index: 756601 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1525. Min Act: -0.0001

Data Index: 366840 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1517. Min Act: -0.0001

Data Index: 988744 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1553. Min Act: -0.0001

Data Index: 603909 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1220598 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1022788 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1108335 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1482. Min Act: -0.0001

Data Index: 828359 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1468. Min Act: -0.0001

Data Index: 21881 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1283474 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1111618 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1449. Min Act: -0.0001

Data Index: 125389 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1156502 (C4 (Web Text))

Max Activating Token Index: 630