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

Dataset: The Pile

Neuron 949 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1585890 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1626058 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1389. Min Act: -0.0000

Data Index: 253109 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1424. Min Act: -0.0000

Data Index: 148788 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1456. Min Act: -0.0000

Data Index: 814767 (The Pile)

Max Activating Token Index: 898

Text #5

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1601331 (The Pile)

Max Activating Token Index: 499

Text #6

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1438. Min Act: -0.0000

Data Index: 508315 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1962422 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1596124 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1061657 (The Pile)

Max Activating Token Index: 890

Text #10

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1672410 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1367. Min Act: -0.0000

Data Index: 102040 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1481673 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1362. Min Act: -0.0000

Data Index: 3382 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1621921 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1699351 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1382. Min Act: -0.0000

Data Index: 494293 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1748449 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1366. Min Act: -0.0001

Data Index: 570029 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1273158 (The Pile)

Max Activating Token Index: 316