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

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

Neuron 3705 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.7063. Min Act: -0.0000

Data Index: 224595 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.8638. Min Act: -0.0000

Data Index: 479438 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.3790. Min Act: -0.0000

Data Index: 1329289 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.6762. Min Act: -0.0000

Data Index: 228034 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.6639. Min Act: -0.0000

Data Index: 1074688 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.2624. Min Act: -0.0000

Data Index: 734844 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.3096. Min Act: -0.0000

Data Index: 1337959 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.2333. Min Act: -0.0000

Data Index: 137574 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.3645. Min Act: -0.0000

Data Index: 1013707 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.0787. Min Act: -0.0000

Data Index: 208893 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.3629. Min Act: -0.0000

Data Index: 59402 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.3552. Min Act: -0.0000

Data Index: 1145772 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.1627. Min Act: -0.0000

Data Index: 242072 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.1472. Min Act: -0.0000

Data Index: 1332779 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.2319. Min Act: -0.0000

Data Index: 781427 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 3.8638. Min Range: -3.8638

Max Act: 2.9394. Min Act: -0.0000

Data Index: 1125567 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.0840. Min Act: -0.0000

Data Index: 90385 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.2169. Min Act: -0.0000

Data Index: 100797 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 3.8638. Min Range: -3.8638

Max Act: 3.0494. Min Act: -0.0000

Data Index: 898918 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 3.8638. Min Range: -3.8638

Max Act: 2.8622. Min Act: -0.0000

Data Index: 1256279 (C4 (Web Text))

Max Activating Token Index: 360