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

Dataset: The Pile

Neuron 146 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: 3.5429. Min Range: -3.5429

Max Act: 3.5380. Min Act: -0.0000

Data Index: 543180 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 3.5429. Min Range: -3.5429

Max Act: 3.5429. Min Act: -0.0000

Data Index: 1737800 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 3.5429. Min Range: -3.5429

Max Act: 3.1440. Min Act: -0.0000

Data Index: 1880881 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 3.5429. Min Range: -3.5429

Max Act: 3.2740. Min Act: -0.0000

Data Index: 1880456 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 3.5429. Min Range: -3.5429

Max Act: 3.3880. Min Act: -0.0000

Data Index: 670643 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 3.5429. Min Range: -3.5429

Max Act: 3.2288. Min Act: -0.0000

Data Index: 1012802 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 3.5429. Min Range: -3.5429

Max Act: 3.0831. Min Act: -0.0000

Data Index: 492398 (The Pile)

Max Activating Token Index: 995

Text #7

Max Range: 3.5429. Min Range: -3.5429

Max Act: 3.1218. Min Act: -0.0000

Data Index: 968592 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.8940. Min Act: -0.0000

Data Index: 527888 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.9520. Min Act: -0.0000

Data Index: 1023364 (The Pile)

Max Activating Token Index: 200

Text #10

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.9131. Min Act: -0.0000

Data Index: 1325217 (The Pile)

Max Activating Token Index: 360

Text #11

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.7655. Min Act: -0.0000

Data Index: 898910 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.7529. Min Act: -0.0000

Data Index: 592330 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.9646. Min Act: -0.0000

Data Index: 800936 (The Pile)

Max Activating Token Index: 561

Text #14

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.9202. Min Act: -0.0000

Data Index: 490312 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.8098. Min Act: -0.0000

Data Index: 1532077 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.9005. Min Act: -0.0000

Data Index: 904163 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.7571. Min Act: -0.0000

Data Index: 671633 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.7328. Min Act: -0.0000

Data Index: 1625240 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.8428. Min Act: -0.0000

Data Index: 1465640 (The Pile)

Max Activating Token Index: 556