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

Dataset: The Pile

Neuron 2340 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2889. Min Act: -0.0000

Data Index: 830512 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1896. Min Act: -0.0000

Data Index: 602865 (The Pile)

Max Activating Token Index: 55

Text #2

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1297515 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1527416 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1089579 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1290899 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1429. Min Act: -0.0000

Data Index: 34882 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1696679 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1077120 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1382. Min Act: -0.0000

Data Index: 866539 (The Pile)

Max Activating Token Index: 826

Text #10

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1430. Min Act: -0.0000

Data Index: 322989 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1320. Min Act: -0.0000

Data Index: 87917 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1087486 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1838168 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1104680 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1150. Min Act: -0.0000

Data Index: 554574 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1286113 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1236. Min Act: -0.0000

Data Index: 633751 (The Pile)

Max Activating Token Index: 200

Text #18

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1294. Min Act: -0.0000

Data Index: 187562 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1380. Min Act: -0.0000

Data Index: 479953 (The Pile)

Max Activating Token Index: 129