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

Dataset: The Pile

Neuron 791 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: 1.3978. Min Range: -1.3978

Max Act: 1.3978. Min Act: -0.0000

Data Index: 155605 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.3671. Min Act: -0.0000

Data Index: 1517561 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2627. Min Act: -0.0000

Data Index: 1668407 (The Pile)

Max Activating Token Index: 614

Text #3

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2416. Min Act: -0.0000

Data Index: 1336319 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2722. Min Act: -0.0000

Data Index: 1348674 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1935718 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1475680 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.1956. Min Act: -0.0000

Data Index: 1327833 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1886587 (The Pile)

Max Activating Token Index: 932

Text #9

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2346. Min Act: -0.0000

Data Index: 1009543 (The Pile)

Max Activating Token Index: 129

Text #10

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2772. Min Act: -0.0000

Data Index: 408531 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0407. Min Act: -0.0000

Data Index: 600060 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0956. Min Act: -0.0000

Data Index: 222984 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1176932 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0669. Min Act: -0.0000

Data Index: 925979 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.1563. Min Act: -0.0000

Data Index: 287993 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1090956 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.1254. Min Act: -0.0000

Data Index: 948178 (The Pile)

Max Activating Token Index: 54

Text #18

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1396432 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.1548. Min Act: -0.0000

Data Index: 438031 (The Pile)

Max Activating Token Index: 221