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

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

Neuron 2861 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1632. Min Act: -0.0003

Data Index: 461187 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1658. Min Act: -0.0003

Data Index: 1075209 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1728. Min Act: -0.0003

Data Index: 406608 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1503. Min Act: -0.0003

Data Index: 860813 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1530. Min Act: -0.0003

Data Index: 569261 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1290. Min Act: -0.0003

Data Index: 323065 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1528. Min Act: -0.0003

Data Index: 1210263 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1479. Min Act: -0.0003

Data Index: 490201 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1455. Min Act: -0.0003

Data Index: 150091 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1440. Min Act: -0.0003

Data Index: 924417 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1510. Min Act: -0.0003

Data Index: 32225 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1587. Min Act: -0.0003

Data Index: 574027 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1424. Min Act: -0.0003

Data Index: 1030212 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1433. Min Act: -0.0003

Data Index: 1356376 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1430. Min Act: -0.0003

Data Index: 420180 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1470. Min Act: -0.0003

Data Index: 256773 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1531. Min Act: -0.0003

Data Index: 379892 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1465. Min Act: -0.0003

Data Index: 1308075 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1449. Min Act: -0.0003

Data Index: 1010380 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1439. Min Act: -0.0003

Data Index: 274610 (C4 (Web Text))

Max Activating Token Index: 40