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

Dataset: The Pile

Neuron 3438 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8693. Min Act: -0.0000

Data Index: 855724 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1357674 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7967. Min Act: -0.0000

Data Index: 47491 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7945. Min Act: -0.0000

Data Index: 591382 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6608. Min Act: -0.0000

Data Index: 392577 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7444. Min Act: -0.0000

Data Index: 258467 (The Pile)

Max Activating Token Index: 590

Text #6

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6724. Min Act: -0.0000

Data Index: 916068 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1719064 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1945507 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1887770 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1450419 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7428. Min Act: -0.0000

Data Index: 109322 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1034826 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.5789. Min Act: -0.0000

Data Index: 176161 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6288. Min Act: -0.0000

Data Index: 276897 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6174. Min Act: -0.0000

Data Index: 444162 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1308969 (The Pile)

Max Activating Token Index: 752

Text #17

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1665445 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.5929. Min Act: -0.0000

Data Index: 429891 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1319897 (The Pile)

Max Activating Token Index: 159