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

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

Neuron 2487 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1632. Min Range: -1.1632

Max Act: 1.1231. Min Act: -0.0000

Data Index: 14358 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 1.1632. Min Range: -1.1632

Max Act: 1.1632. Min Act: -0.0000

Data Index: 889272 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.9420. Min Act: -0.0000

Data Index: 632117 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1117715 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1167332 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.9139. Min Act: -0.0000

Data Index: 370682 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1264179 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.8508. Min Act: -0.0000

Data Index: 437807 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.8995. Min Act: -0.0000

Data Index: 494807 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.8606. Min Act: -0.0000

Data Index: 475204 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1141128 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.8462. Min Act: -0.0000

Data Index: 301961 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.8109. Min Act: -0.0000

Data Index: 224512 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.7624. Min Act: -0.0000

Data Index: 242905 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.7402. Min Act: -0.0000

Data Index: 496771 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.7077. Min Act: -0.0000

Data Index: 729567 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.7481. Min Act: -0.0000

Data Index: 367003 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1233492 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.7224. Min Act: -0.0000

Data Index: 416206 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.1632. Min Range: -1.1632

Max Act: 0.7342. Min Act: -0.0000

Data Index: 818138 (C4 (Web Text))

Max Activating Token Index: 104