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

Dataset: The Pile

Neuron 811 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.4692. Min Act: -0.0000

Data Index: 499389 (The Pile)

Max Activating Token Index: 602

Text #1

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.2509. Min Act: -0.0000

Data Index: 1490014 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1746618 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1653832 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1502738 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1716091 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.0087. Min Act: -0.0000

Data Index: 1748323 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1470054 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1956339 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1601939 (The Pile)

Max Activating Token Index: 544

Text #10

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1818963 (The Pile)

Max Activating Token Index: 601

Text #11

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.8817. Min Act: -0.0000

Data Index: 996711 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1066846 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9408. Min Act: 0.0000

Data Index: 1444956 (The Pile)

Max Activating Token Index: 79

Text #14

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.8207. Min Act: -0.0000

Data Index: 887857 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1717758 (The Pile)

Max Activating Token Index: 776

Text #16

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9421. Min Act: -0.0000

Data Index: 20185 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1095709 (The Pile)

Max Activating Token Index: 664

Text #18

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9499. Min Act: -0.0000

Data Index: 727444 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9499. Min Act: -0.0000

Data Index: 1743986 (The Pile)

Max Activating Token Index: 704