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

Dataset: The Pile

Neuron 128 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: 0.9564. Min Range: -0.9564

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1104560 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8443. Min Act: -0.0000

Data Index: 295622 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.9204. Min Act: -0.0000

Data Index: 565658 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.9246. Min Act: -0.0000

Data Index: 928103 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1394129 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1993468 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1398908 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.9071. Min Act: -0.0000

Data Index: 805795 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1554803 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1262385 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1366170 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1379917 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.7916. Min Act: -0.0000

Data Index: 489557 (The Pile)

Max Activating Token Index: 510

Text #13

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1328968 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1827401 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1704358 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.7419. Min Act: -0.0000

Data Index: 650379 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1562864 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1983555 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1474079 (The Pile)

Max Activating Token Index: 595