Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2548 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.6415. Min Act: -0.0001

Data Index: 223229 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.6149. Min Act: -0.0001

Data Index: 499430 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5660. Min Act: -0.0001

Data Index: 1138202 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5449. Min Act: -0.0002

Data Index: 400647 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5319. Min Act: -0.0001

Data Index: 235845 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5277. Min Act: -0.0001

Data Index: 563005 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4770. Min Act: -0.0001

Data Index: 324626 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5680. Min Act: -0.0001

Data Index: 487288 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5036. Min Act: -0.0002

Data Index: 8752 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4848. Min Act: -0.0001

Data Index: 1266598 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4870. Min Act: -0.0001

Data Index: 759881 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4719. Min Act: -0.0001

Data Index: 111071 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4789. Min Act: -0.0002

Data Index: 1142531 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4764. Min Act: -0.0001

Data Index: 429942 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4572. Min Act: -0.0001

Data Index: 947422 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4772. Min Act: -0.0002

Data Index: 711656 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4579. Min Act: -0.0002

Data Index: 627591 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4562. Min Act: -0.0001

Data Index: 264552 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4510. Min Act: -0.0001

Data Index: 216165 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4536. Min Act: -0.0002

Data Index: 46295 (C4 (Web Text))

Max Activating Token Index: 401