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

Dataset: The Pile

Neuron 2530 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: 7.1131. Min Range: -7.1131

Max Act: 7.1131. Min Act: -0.0000

Data Index: 271552 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 7.1131. Min Range: -7.1131

Max Act: 6.8743. Min Act: -0.0000

Data Index: 1683951 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 7.1131. Min Range: -7.1131

Max Act: 6.6923. Min Act: -0.0000

Data Index: 1563056 (The Pile)

Max Activating Token Index: 823

Text #3

Max Range: 7.1131. Min Range: -7.1131

Max Act: 6.0997. Min Act: -0.0000

Data Index: 558635 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.4618. Min Act: -0.0000

Data Index: 755040 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.9351. Min Act: -0.0000

Data Index: 1046586 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.8232. Min Act: -0.0000

Data Index: 700792 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 7.1131. Min Range: -7.1131

Max Act: 6.1891. Min Act: -0.0000

Data Index: 361222 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.5098. Min Act: -0.0000

Data Index: 872322 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.6759. Min Act: -0.0000

Data Index: 1950028 (The Pile)

Max Activating Token Index: 946

Text #10

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.5699. Min Act: -0.0000

Data Index: 1306201 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.3440. Min Act: -0.0000

Data Index: 1567926 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.5470. Min Act: -0.0000

Data Index: 1021944 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.1365. Min Act: -0.0000

Data Index: 1149025 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.2995. Min Act: -0.0000

Data Index: 671229 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.4810. Min Act: -0.0000

Data Index: 1947772 (The Pile)

Max Activating Token Index: 684

Text #16

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.2634. Min Act: -0.0000

Data Index: 1415298 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.0200. Min Act: -0.0000

Data Index: 406569 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 7.1131. Min Range: -7.1131

Max Act: 5.4303. Min Act: -0.0000

Data Index: 14312 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 7.1131. Min Range: -7.1131

Max Act: 4.9820. Min Act: -0.0000

Data Index: 801203 (The Pile)

Max Activating Token Index: 59