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

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

Neuron 3907 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: 0.6485. Min Range: -0.6485

Max Act: 0.6485. Min Act: -0.0000

Data Index: 947456 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5586. Min Act: -0.0000

Data Index: 556734 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5677. Min Act: -0.0000

Data Index: 426732 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.6073. Min Act: -0.0000

Data Index: 332876 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1144674 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.6346. Min Act: -0.0000

Data Index: 587932 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5513. Min Act: -0.0000

Data Index: 238084 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5083. Min Act: -0.0000

Data Index: 203228 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1259273 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5753. Min Act: -0.0000

Data Index: 82060 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5090. Min Act: -0.0000

Data Index: 928485 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4911. Min Act: -0.0000

Data Index: 42118 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5655. Min Act: -0.0000

Data Index: 754718 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1302238 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5422. Min Act: -0.0000

Data Index: 755459 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5467. Min Act: -0.0000

Data Index: 496525 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4927. Min Act: -0.0000

Data Index: 895623 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5414. Min Act: -0.0000

Data Index: 337320 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1112412 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5530. Min Act: -0.0000

Data Index: 421847 (C4 (Web Text))

Max Activating Token Index: 831