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

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

Neuron 576 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.8922. Min Act: -0.0000

Data Index: 949671 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1288695 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6913. Min Act: -0.0000

Data Index: 27799 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6457. Min Act: -0.0000

Data Index: 651018 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6886. Min Act: -0.0000

Data Index: 498899 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.5784. Min Act: -0.0000

Data Index: 543093 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6111. Min Act: -0.0000

Data Index: 667442 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1334370 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.5434. Min Act: -0.0000

Data Index: 527504 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.5687. Min Act: -0.0000

Data Index: 830243 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.5390. Min Act: -0.0000

Data Index: 13803 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1171810 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.5431. Min Act: -0.0000

Data Index: 121249 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.4978. Min Act: -0.0000

Data Index: 249693 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.4943. Min Act: -0.0000

Data Index: 780911 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.4642. Min Act: -0.0000

Data Index: 761952 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.4628. Min Act: -0.0000

Data Index: 537857 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.4734. Min Act: -0.0000

Data Index: 736052 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1136310 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1229076 (C4 (Web Text))

Max Activating Token Index: 657