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

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

Neuron 45 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0395. Min Act: -0.0000

Data Index: 650482 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.9223. Min Act: 0.0000

Data Index: 228597 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0977. Min Act: 0.0000

Data Index: 514072 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.8891. Min Act: -0.0000

Data Index: 1079413 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.8609. Min Act: -0.0000

Data Index: 772167 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7809. Min Act: -0.0000

Data Index: 1095316 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.8576. Min Act: -0.0000

Data Index: 353977 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.8409. Min Act: 0.0000

Data Index: 163747 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7783. Min Act: 0.0001

Data Index: 790244 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.8133. Min Act: -0.0000

Data Index: 1071208 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.8054. Min Act: 0.0000

Data Index: 808779 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7495. Min Act: 0.0000

Data Index: 391929 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.6970. Min Act: 0.0000

Data Index: 996497 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.8313. Min Act: 0.0001

Data Index: 540026 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7355. Min Act: -0.0000

Data Index: 520408 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.6387. Min Act: -0.0000

Data Index: 438281 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7761. Min Act: -0.0000

Data Index: 1291727 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7150. Min Act: -0.0000

Data Index: 1200274 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7166. Min Act: -0.0000

Data Index: 904491 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7030. Min Act: -0.0000

Data Index: 1145709 (C4 (Web Text))

Max Activating Token Index: 361