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

Dataset: The Pile

Neuron 388 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.0258. Min Range: -3.0258

Max Act: 3.0258. Min Act: -0.0000

Data Index: 1172422 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 3.0258. Min Range: -3.0258

Max Act: 2.2975. Min Act: -0.0000

Data Index: 912466 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 3.0258. Min Range: -3.0258

Max Act: 2.3033. Min Act: -0.0000

Data Index: 1743504 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 3.0258. Min Range: -3.0258

Max Act: 2.1882. Min Act: -0.0000

Data Index: 384821 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.8722. Min Act: -0.0000

Data Index: 1655910 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.9553. Min Act: -0.0000

Data Index: 945112 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.7865. Min Act: -0.0000

Data Index: 936543 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.7629. Min Act: -0.0000

Data Index: 1033691 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.6160. Min Act: -0.0000

Data Index: 1441869 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.6544. Min Act: -0.0000

Data Index: 303728 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.4692. Min Act: -0.0000

Data Index: 298022 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.6616. Min Act: -0.0000

Data Index: 382731 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.5595. Min Act: -0.0000

Data Index: 707872 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.3810. Min Act: -0.0000

Data Index: 302666 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.4923. Min Act: -0.0000

Data Index: 1504990 (The Pile)

Max Activating Token Index: 873

Text #15

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1020046 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.3964. Min Act: -0.0000

Data Index: 338221 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1619701 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.2623. Min Act: -0.0000

Data Index: 627133 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 3.0258. Min Range: -3.0258

Max Act: 1.3287. Min Act: -0.0000

Data Index: 1983678 (The Pile)

Max Activating Token Index: 753