Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 560 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1549512 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1116733 (The Pile)

Max Activating Token Index: 435

Text #2

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1292256 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1559. Min Act: -0.0000

Data Index: 254625 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1095945 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1619. Min Act: -0.0000

Data Index: 707769 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1314961 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1539418 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1325. Min Act: -0.0000

Data Index: 914661 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1040874 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1360. Min Act: -0.0000

Data Index: 299137 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1399. Min Act: -0.0000

Data Index: 275518 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1174761 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1270237 (The Pile)

Max Activating Token Index: 301

Text #14

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1430. Min Act: -0.0000

Data Index: 650703 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1388404 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1757932 (The Pile)

Max Activating Token Index: 893

Text #17

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1278. Min Act: -0.0000

Data Index: 157502 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1264. Min Act: -0.0000

Data Index: 520999 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1372632 (The Pile)

Max Activating Token Index: 103