Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3374 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.8818. Min Act: -0.0000

Data Index: 1215257 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.7911. Min Act: -0.0000

Data Index: 1979501 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.7681. Min Act: -0.0000

Data Index: 1573762 (The Pile)

Max Activating Token Index: 2

Text #3

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6621. Min Act: -0.0000

Data Index: 1568638 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.8561. Min Act: -0.0000

Data Index: 1627447 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6358. Min Act: -0.0000

Data Index: 1423476 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.7816. Min Act: -0.0000

Data Index: 1682763 (The Pile)

Max Activating Token Index: 828

Text #7

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.5576. Min Act: -0.0000

Data Index: 1562111 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6035. Min Act: -0.0000

Data Index: 926070 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6444. Min Act: -0.0000

Data Index: 1842356 (The Pile)

Max Activating Token Index: 463

Text #10

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6387. Min Act: -0.0000

Data Index: 1174711 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6366. Min Act: -0.0000

Data Index: 902110 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.5460. Min Act: -0.0000

Data Index: 1467485 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1632032 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1733597 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1331492 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6169. Min Act: -0.0000

Data Index: 1425905 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6050. Min Act: -0.0000

Data Index: 994780 (The Pile)

Max Activating Token Index: 264

Text #18

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.5969. Min Act: -0.0000

Data Index: 1045782 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.6605. Min Act: -0.0000

Data Index: 1087889 (The Pile)

Max Activating Token Index: 26