Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 29 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0562. Min Act: -0.0003

Data Index: 149105 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0543. Min Act: -0.0003

Data Index: 298017 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1003241 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0531. Min Act: -0.0003

Data Index: 429518 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1148809 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1181497 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0469. Min Act: -0.0003

Data Index: 206973 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1219752 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0462. Min Act: -0.0003

Data Index: 161429 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0477. Min Act: -0.0003

Data Index: 681951 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0451. Min Act: -0.0003

Data Index: 891116 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1349192 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1154234 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0440. Min Act: -0.0003

Data Index: 191759 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0449. Min Act: -0.0003

Data Index: 76961 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0445. Min Act: -0.0003

Data Index: 697544 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0462. Min Act: -0.0003

Data Index: 488661 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1231103 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1279754 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1280315 (C4 (Web Text))

Max Activating Token Index: 225