Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1127 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6088. Min Range: -4.6088

Max Act: 4.6088. Min Act: -0.0000

Data Index: 137033 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 4.6088. Min Range: -4.6088

Max Act: 4.0141. Min Act: -0.0000

Data Index: 392810 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.3768. Min Act: -0.0000

Data Index: 990879 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.6592. Min Act: -0.0000

Data Index: 1020958 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.7351. Min Act: -0.0000

Data Index: 1167606 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.9217. Min Act: -0.0000

Data Index: 588421 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.7391. Min Act: -0.0000

Data Index: 1020600 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.7330. Min Act: -0.0000

Data Index: 1087700 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.6810. Min Act: -0.0000

Data Index: 322149 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.6116. Min Act: -0.0000

Data Index: 1335614 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.6044. Min Act: -0.0000

Data Index: 1004939 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.5944. Min Act: -0.0000

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.5896. Min Act: -0.0000

Data Index: 336541 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.7450. Min Act: -0.0000

Data Index: 249784 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.5644. Min Act: -0.0000

Data Index: 1045356 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.4105. Min Act: -0.0000

Data Index: 565370 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.5837. Min Act: -0.0000

Data Index: 1006155 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.5383. Min Act: -0.0000

Data Index: 862521 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.5012. Min Act: -0.0000

Data Index: 675183 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 4.6088. Min Range: -4.6088

Max Act: 3.3589. Min Act: -0.0000

Data Index: 881303 (C4 (Web Text))

Max Activating Token Index: 393