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

Dataset: The Pile

Neuron 4913 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.6635. Min Act: -0.0000

Data Index: 1885080 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5808. Min Act: -0.0000

Data Index: 769642 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.6075. Min Act: -0.0000

Data Index: 127152 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4248. Min Act: -0.0000

Data Index: 263846 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4350. Min Act: -0.0000

Data Index: 327661 (The Pile)

Max Activating Token Index: 95

Text #5

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.3439. Min Act: -0.0000

Data Index: 1872970 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1024992 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1878. Min Act: -0.0000

Data Index: 1497449 (The Pile)

Max Activating Token Index: 909

Text #8

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.2542. Min Act: 0.0000

Data Index: 1287587 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1716160 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.2402. Min Act: -0.0000

Data Index: 116795 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1313. Min Act: -0.0000

Data Index: 732171 (The Pile)

Max Activating Token Index: 652

Text #12

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1084. Min Act: -0.0000

Data Index: 1060760 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1060. Min Act: -0.0000

Data Index: 114429 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1450154 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1352371 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1700330 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1206512 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1317746 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1389. Min Act: -0.0000

Data Index: 157098 (The Pile)

Max Activating Token Index: 1001