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

Dataset: The Pile

Neuron 544 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: 4.0691. Min Range: -4.0691

Max Act: 4.0691. Min Act: -0.0000

Data Index: 1518712 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.6014. Min Act: -0.0000

Data Index: 335650 (The Pile)

Max Activating Token Index: 963

Text #2

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.1236. Min Act: -0.0000

Data Index: 637766 (The Pile)

Max Activating Token Index: 926

Text #3

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.6572. Min Act: -0.0000

Data Index: 1099818 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7943. Min Act: -0.0000

Data Index: 954304 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.4789. Min Act: -0.0000

Data Index: 936116 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.4709. Min Act: -0.0000

Data Index: 707387 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.1456. Min Act: -0.0000

Data Index: 565652 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.2219. Min Act: -0.0000

Data Index: 657968 (The Pile)

Max Activating Token Index: 739

Text #9

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.5094. Min Act: -0.0000

Data Index: 776104 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 4.0691. Min Range: -4.0691

Max Act: 2.7649. Min Act: -0.0000

Data Index: 206342 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.1927. Min Act: -0.0000

Data Index: 324317 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.3303. Min Act: -0.0000

Data Index: 1760307 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.1496. Min Act: -0.0000

Data Index: 1736115 (The Pile)

Max Activating Token Index: 188

Text #14

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.2991. Min Act: -0.0000

Data Index: 839423 (The Pile)

Max Activating Token Index: 375

Text #15

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.1511. Min Act: -0.0000

Data Index: 60738 (The Pile)

Max Activating Token Index: 798

Text #16

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.2633. Min Act: -0.0000

Data Index: 1079367 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.4172. Min Act: -0.0000

Data Index: 672163 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.2469. Min Act: -0.0000

Data Index: 1868356 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.4067. Min Act: -0.0000

Data Index: 1405243 (The Pile)

Max Activating Token Index: 961