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

Dataset: The Pile

Neuron 1137 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: 1.7758. Min Range: -1.7758

Max Act: 1.7416. Min Act: -0.0000

Data Index: 1402279 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.7758. Min Act: -0.0000

Data Index: 920686 (The Pile)

Max Activating Token Index: 784

Text #2

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.4952. Min Act: -0.0000

Data Index: 966079 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.6252. Min Act: -0.0000

Data Index: 533085 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5577. Min Act: -0.0000

Data Index: 1957403 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.3081. Min Act: -0.0000

Data Index: 477773 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.6263. Min Act: -0.0000

Data Index: 230517 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.3671. Min Act: -0.0000

Data Index: 679489 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5576. Min Act: -0.0000

Data Index: 1959404 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.2655. Min Act: -0.0000

Data Index: 1309230 (The Pile)

Max Activating Token Index: 845

Text #10

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.4875. Min Act: -0.0000

Data Index: 64559 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.3562. Min Act: -0.0000

Data Index: 913830 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.6254. Min Act: -0.0000

Data Index: 1491490 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.1495. Min Act: -0.0000

Data Index: 1290900 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.4672. Min Act: -0.0000

Data Index: 576308 (The Pile)

Max Activating Token Index: 864

Text #15

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1396695 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.3988. Min Act: -0.0000

Data Index: 842605 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.2467. Min Act: -0.0000

Data Index: 416397 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.2520. Min Act: -0.0000

Data Index: 887624 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.1995. Min Act: -0.0000

Data Index: 925001 (The Pile)

Max Activating Token Index: 882