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

Dataset: The Pile

Neuron 1819 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1605. Min Act: -0.0000

Data Index: 945784 (The Pile)

Max Activating Token Index: 546

Text #1

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1276. Min Act: -0.0000

Data Index: 700092 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0885. Min Act: -0.0000

Data Index: 255716 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1238. Min Act: -0.0000

Data Index: 1954389 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1218. Min Act: -0.0000

Data Index: 974166 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1065087 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0940. Min Act: -0.0000

Data Index: 1962928 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1159. Min Act: -0.0000

Data Index: 1759873 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1668. Min Act: -0.0000

Data Index: 541731 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1558. Min Act: -0.0000

Data Index: 244639 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0515. Min Act: -0.0000

Data Index: 33453 (The Pile)

Max Activating Token Index: 1014

Text #11

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0585. Min Act: -0.0000

Data Index: 468455 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0558. Min Act: -0.0000

Data Index: 1385506 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1802891 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.9900. Min Act: -0.0000

Data Index: 973321 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1585916 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0494. Min Act: -0.0000

Data Index: 771747 (The Pile)

Max Activating Token Index: 303

Text #17

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1134745 (The Pile)

Max Activating Token Index: 282

Text #18

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1244804 (The Pile)

Max Activating Token Index: 533

Text #19

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0402. Min Act: -0.0000

Data Index: 378256 (The Pile)

Max Activating Token Index: 252