Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1485 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 7.7438. Min Range: -7.7438

Max Act: 7.7438. Min Act: -0.0000

Data Index: 768972 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.8468. Min Act: -0.0000

Data Index: 35627 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 7.7438. Min Range: -7.7438

Max Act: 7.0820. Min Act: -0.0000

Data Index: 28420 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.8273. Min Act: -0.0000

Data Index: 962933 (The Pile)

Max Activating Token Index: 955

Text #4

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.3093. Min Act: -0.0000

Data Index: 408393 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.1335. Min Act: -0.0000

Data Index: 1412292 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.4063. Min Act: -0.0000

Data Index: 1964888 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.2452. Min Act: -0.0000

Data Index: 1785500 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 7.7438. Min Range: -7.7438

Max Act: 5.9640. Min Act: -0.0000

Data Index: 750075 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 7.7438. Min Range: -7.7438

Max Act: 5.8951. Min Act: -0.0000

Data Index: 1512755 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.4333. Min Act: -0.0000

Data Index: 721035 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.6368. Min Act: -0.0000

Data Index: 19437 (The Pile)

Max Activating Token Index: 532

Text #12

Max Range: 7.7438. Min Range: -7.7438

Max Act: 5.9138. Min Act: -0.0000

Data Index: 1452201 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.1385. Min Act: -0.0000

Data Index: 1172116 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.4655. Min Act: -0.0000

Data Index: 1174556 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.2908. Min Act: -0.0000

Data Index: 223545 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 7.7438. Min Range: -7.7438

Max Act: 5.6799. Min Act: -0.0000

Data Index: 780155 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 7.7438. Min Range: -7.7438

Max Act: 5.7361. Min Act: -0.0000

Data Index: 566975 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 7.7438. Min Range: -7.7438

Max Act: 6.0741. Min Act: -0.0000

Data Index: 760448 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 7.7438. Min Range: -7.7438

Max Act: 5.4584. Min Act: -0.0000

Data Index: 409584 (The Pile)

Max Activating Token Index: 884