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

Dataset: The Pile

Neuron 3535 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: 0.5787. Min Range: -0.5787

Max Act: 0.5787. Min Act: -0.0000

Data Index: 392879 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.5665. Min Act: -0.0000

Data Index: 875900 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.5731. Min Act: -0.0000

Data Index: 100438 (The Pile)

Max Activating Token Index: 341

Text #3

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.5302. Min Act: -0.0000

Data Index: 596110 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1700207 (The Pile)

Max Activating Token Index: 397

Text #5

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1345571 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1855912 (The Pile)

Max Activating Token Index: 703

Text #7

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1404767 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.5243. Min Act: -0.0000

Data Index: 557198 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.5162. Min Act: -0.0000

Data Index: 193894 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1003068 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.5091. Min Act: -0.0000

Data Index: 307017 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1643131 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.4715. Min Act: -0.0000

Data Index: 972637 (The Pile)

Max Activating Token Index: 698

Text #14

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.4980. Min Act: -0.0000

Data Index: 105150 (The Pile)

Max Activating Token Index: 181

Text #15

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1269865 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.4802. Min Act: -0.0000

Data Index: 384871 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1113266 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.4805. Min Act: -0.0000

Data Index: 97253 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 0.5787. Min Range: -0.5787

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1919151 (The Pile)

Max Activating Token Index: 601