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

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

Neuron 3940 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: 2.9099. Min Range: -2.9099

Max Act: 2.8411. Min Act: -0.0000

Data Index: 697244 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.9099. Min Act: -0.0000

Data Index: 366867 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.5001. Min Act: -0.0000

Data Index: 148695 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.5352. Min Act: -0.0000

Data Index: 537079 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.4040. Min Act: -0.0000

Data Index: 1231003 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.7812. Min Act: -0.0000

Data Index: 319922 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.4026. Min Act: -0.0000

Data Index: 631570 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.2577. Min Act: -0.0000

Data Index: 904847 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.0675. Min Act: -0.0000

Data Index: 819270 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.0559. Min Act: -0.0000

Data Index: 656842 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.1506. Min Act: -0.0000

Data Index: 761549 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.1281. Min Act: -0.0000

Data Index: 724518 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.0204. Min Act: -0.0000

Data Index: 480319 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 2.9099. Min Range: -2.9099

Max Act: 1.9881. Min Act: -0.0000

Data Index: 203152 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.0979. Min Act: -0.0000

Data Index: 1137509 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.0999. Min Act: -0.0000

Data Index: 824777 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.0224. Min Act: -0.0000

Data Index: 860322 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.0443. Min Act: -0.0000

Data Index: 1009386 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 2.9099. Min Range: -2.9099

Max Act: 1.9014. Min Act: -0.0000

Data Index: 54882 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 2.9099. Min Range: -2.9099

Max Act: 2.0128. Min Act: -0.0000

Data Index: 1065170 (C4 (Web Text))

Max Activating Token Index: 483