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

Dataset: The Pile

Neuron 803 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.7125. Min Act: -0.0000

Data Index: 913449 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1787136 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.7160. Min Act: 0.0000

Data Index: 538356 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6754. Min Act: -0.0000

Data Index: 97885 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6178. Min Act: -0.0000

Data Index: 704146 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1434082 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1822769 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5096. Min Act: -0.0000

Data Index: 718675 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1405176 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5515. Min Act: -0.0000

Data Index: 357420 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5321. Min Act: -0.0000

Data Index: 420714 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1586699 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1292129 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1425857 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1765636 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1124672 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.4744. Min Act: -0.0000

Data Index: 33159 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.4489. Min Act: -0.0000

Data Index: 44426 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1799578 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1114025 (The Pile)

Max Activating Token Index: 546