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

Dataset: The Pile

Neuron 2199 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: 0.3352. Min Range: -0.3352

Max Act: 0.2785. Min Act: -0.0000

Data Index: 249999 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1989553 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1377616 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.3233. Min Act: -0.0000

Data Index: 816563 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1067699 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2797. Min Act: -0.0000

Data Index: 431032 (The Pile)

Max Activating Token Index: 30

Text #6

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2972. Min Act: -0.0000

Data Index: 552748 (The Pile)

Max Activating Token Index: 325

Text #7

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1022088 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2611. Min Act: -0.0000

Data Index: 991672 (The Pile)

Max Activating Token Index: 875

Text #9

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1380513 (The Pile)

Max Activating Token Index: 136

Text #10

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1450951 (The Pile)

Max Activating Token Index: 542

Text #11

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1566010 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1307315 (The Pile)

Max Activating Token Index: 527

Text #13

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2577. Min Act: -0.0000

Data Index: 841463 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1168530 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2519. Min Act: -0.0000

Data Index: 621547 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2505. Min Act: -0.0000

Data Index: 801503 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1997358 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1875807 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2291. Min Act: -0.0000

Data Index: 305168 (The Pile)

Max Activating Token Index: 396