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

Dataset: The Pile

Neuron 1315 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 5.3692. Min Range: -5.3692

Max Act: 5.3692. Min Act: -0.0000

Data Index: 1979292 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 5.3692. Min Range: -5.3692

Max Act: 4.7768. Min Act: -0.0000

Data Index: 913841 (The Pile)

Max Activating Token Index: 807

Text #2

Max Range: 5.3692. Min Range: -5.3692

Max Act: 4.3068. Min Act: -0.0000

Data Index: 1577756 (The Pile)

Max Activating Token Index: 738

Text #3

Max Range: 5.3692. Min Range: -5.3692

Max Act: 4.2795. Min Act: -0.0000

Data Index: 389449 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 5.3692. Min Range: -5.3692

Max Act: 4.4306. Min Act: -0.0000

Data Index: 770235 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 5.3692. Min Range: -5.3692

Max Act: 4.3248. Min Act: -0.0000

Data Index: 503487 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 5.3692. Min Range: -5.3692

Max Act: 4.2821. Min Act: -0.0000

Data Index: 864764 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.9231. Min Act: -0.0000

Data Index: 1768968 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.7188. Min Act: -0.0000

Data Index: 1839843 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.7557. Min Act: -0.0000

Data Index: 681396 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.8883. Min Act: -0.0000

Data Index: 240778 (The Pile)

Max Activating Token Index: 730

Text #11

Max Range: 5.3692. Min Range: -5.3692

Max Act: 4.0862. Min Act: -0.0000

Data Index: 1375227 (The Pile)

Max Activating Token Index: 774

Text #12

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.8709. Min Act: -0.0000

Data Index: 349941 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.8632. Min Act: -0.0000

Data Index: 926582 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.7228. Min Act: -0.0000

Data Index: 570537 (The Pile)

Max Activating Token Index: 525

Text #15

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.9742. Min Act: -0.0000

Data Index: 766084 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.5857. Min Act: -0.0000

Data Index: 1554663 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.5619. Min Act: -0.0000

Data Index: 548777 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.5467. Min Act: -0.0000

Data Index: 1696753 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 5.3692. Min Range: -5.3692

Max Act: 3.5622. Min Act: -0.0000

Data Index: 1893448 (The Pile)

Max Activating Token Index: 444