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

Dataset: The Pile

Neuron 3261 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: 1.0457. Min Range: -1.0457

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1655964 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 1.0457. Min Range: -1.0457

Max Act: 1.0240. Min Act: -0.0000

Data Index: 580965 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.9420. Min Act: -0.0000

Data Index: 871463 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1614978 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.9017. Min Act: -0.0000

Data Index: 38761 (The Pile)

Max Activating Token Index: 610

Text #5

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8764. Min Act: -0.0000

Data Index: 427231 (The Pile)

Max Activating Token Index: 570

Text #6

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8908. Min Act: -0.0000

Data Index: 116428 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8103. Min Act: -0.0000

Data Index: 325547 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1558260 (The Pile)

Max Activating Token Index: 800

Text #9

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1868676 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1144605 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1951638 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1745641 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7998. Min Act: -0.0000

Data Index: 887374 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7970. Min Act: -0.0000

Data Index: 301221 (The Pile)

Max Activating Token Index: 441

Text #15

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7589. Min Act: -0.0000

Data Index: 661866 (The Pile)

Max Activating Token Index: 95

Text #16

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8361. Min Act: -0.0000

Data Index: 798981 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1425008 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7621. Min Act: -0.0000

Data Index: 29079 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7646. Min Act: -0.0000

Data Index: 903747 (The Pile)

Max Activating Token Index: 548