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

Dataset: The Pile

Neuron 821 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: 1.5305. Min Range: -1.5305

Max Act: 1.5305. Min Act: -0.0000

Data Index: 1180190 (The Pile)

Max Activating Token Index: 306

Text #1

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.4798. Min Act: -0.0000

Data Index: 95210 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.5112. Min Act: -0.0000

Data Index: 145168 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.2377. Min Act: -0.0000

Data Index: 546079 (The Pile)

Max Activating Token Index: 594

Text #4

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.1868. Min Act: -0.0000

Data Index: 61992 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.2505. Min Act: -0.0000

Data Index: 1376858 (The Pile)

Max Activating Token Index: 100

Text #6

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.2248. Min Act: -0.0000

Data Index: 619952 (The Pile)

Max Activating Token Index: 288

Text #7

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.2756. Min Act: -0.0000

Data Index: 1008535 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.1744. Min Act: -0.0000

Data Index: 24526 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.2373. Min Act: -0.0000

Data Index: 778235 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1203561 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1231025 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1000039 (The Pile)

Max Activating Token Index: 297

Text #13

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.1100. Min Act: -0.0000

Data Index: 433076 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.2793. Min Act: -0.0000

Data Index: 674667 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.2002. Min Act: -0.0000

Data Index: 1566964 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 1.5305. Min Range: -1.5305

Max Act: 0.9894. Min Act: -0.0000

Data Index: 565804 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1419203 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1815970 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 1.5305. Min Range: -1.5305

Max Act: 1.0433. Min Act: -0.0000

Data Index: 789199 (The Pile)

Max Activating Token Index: 664