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

Dataset: The Pile

Neuron 1582 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: 5.1809. Min Range: -5.1809

Max Act: 5.1809. Min Act: -0.0000

Data Index: 1156876 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 5.1809. Min Range: -5.1809

Max Act: 5.1433. Min Act: -0.0000

Data Index: 220499 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 5.1809. Min Range: -5.1809

Max Act: 4.8414. Min Act: -0.0000

Data Index: 376192 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 5.1809. Min Range: -5.1809

Max Act: 4.8017. Min Act: -0.0000

Data Index: 1836236 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 5.1809. Min Range: -5.1809

Max Act: 5.1477. Min Act: -0.0000

Data Index: 1221846 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 5.1809. Min Range: -5.1809

Max Act: 4.5469. Min Act: -0.0000

Data Index: 1864407 (The Pile)

Max Activating Token Index: 855

Text #6

Max Range: 5.1809. Min Range: -5.1809

Max Act: 4.2466. Min Act: -0.0000

Data Index: 257914 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 5.1809. Min Range: -5.1809

Max Act: 4.3751. Min Act: -0.0000

Data Index: 384841 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 5.1809. Min Range: -5.1809

Max Act: 4.0283. Min Act: -0.0000

Data Index: 399929 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 5.1809. Min Range: -5.1809

Max Act: 3.7875. Min Act: -0.0000

Data Index: 542050 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 5.1809. Min Range: -5.1809

Max Act: 3.9858. Min Act: -0.0000

Data Index: 732884 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 5.1809. Min Range: -5.1809

Max Act: 4.1308. Min Act: -0.0000

Data Index: 1337199 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 5.1809. Min Range: -5.1809

Max Act: 4.1328. Min Act: -0.0000

Data Index: 165940 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 5.1809. Min Range: -5.1809

Max Act: 3.8018. Min Act: -0.0000

Data Index: 459358 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 5.1809. Min Range: -5.1809

Max Act: 3.7537. Min Act: -0.0000

Data Index: 591542 (The Pile)

Max Activating Token Index: 559

Text #15

Max Range: 5.1809. Min Range: -5.1809

Max Act: 3.7261. Min Act: -0.0000

Data Index: 1228651 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 5.1809. Min Range: -5.1809

Max Act: 3.8440. Min Act: -0.0000

Data Index: 553985 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 5.1809. Min Range: -5.1809

Max Act: 3.5973. Min Act: -0.0000

Data Index: 896874 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 5.1809. Min Range: -5.1809

Max Act: 4.0985. Min Act: -0.0000

Data Index: 1418314 (The Pile)

Max Activating Token Index: 266

Text #19

Max Range: 5.1809. Min Range: -5.1809

Max Act: 3.3906. Min Act: -0.0000

Data Index: 1794359 (The Pile)

Max Activating Token Index: 29