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

Dataset: The Pile

Neuron 703 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: 0.6483. Min Range: -0.6483

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1479393 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1662896 (The Pile)

Max Activating Token Index: 896

Text #2

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1103353 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1642427 (The Pile)

Max Activating Token Index: 644

Text #4

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1947040 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4567. Min Act: -0.0000

Data Index: 485120 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1954796 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1793539 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3944. Min Act: -0.0000

Data Index: 731663 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1192029 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1561552 (The Pile)

Max Activating Token Index: 780

Text #11

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1484196 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1567273 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4256. Min Act: -0.0000

Data Index: 182917 (The Pile)

Max Activating Token Index: 1008

Text #14

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1454272 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3942. Min Act: -0.0000

Data Index: 639793 (The Pile)

Max Activating Token Index: 405

Text #16

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3528. Min Act: -0.0000

Data Index: 344362 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3771. Min Act: -0.0000

Data Index: 160592 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1107183 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1128389 (The Pile)

Max Activating Token Index: 404