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

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

Neuron 3985 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0635. Min Range: -1.0635

Max Act: 1.0635. Min Act: -0.0001

Data Index: 1126874 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9935. Min Act: -0.0001

Data Index: 156758 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 1.0635. Min Range: -1.0635

Max Act: 1.0450. Min Act: -0.0001

Data Index: 758540 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 1.0635. Min Range: -1.0635

Max Act: 1.0555. Min Act: -0.0001

Data Index: 876057 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9400. Min Act: -0.0001

Data Index: 491035 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9086. Min Act: -0.0001

Data Index: 248405 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9525. Min Act: -0.0001

Data Index: 766462 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9338. Min Act: -0.0001

Data Index: 1123564 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9291. Min Act: -0.0001

Data Index: 1145777 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9073. Min Act: -0.0001

Data Index: 93208 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9087. Min Act: -0.0001

Data Index: 1044301 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8615. Min Act: -0.0001

Data Index: 75665 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8734. Min Act: -0.0001

Data Index: 852438 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8751. Min Act: -0.0001

Data Index: 473802 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9397. Min Act: -0.0001

Data Index: 481576 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9043. Min Act: -0.0001

Data Index: 705494 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8509. Min Act: -0.0001

Data Index: 442787 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8740. Min Act: -0.0001

Data Index: 200303 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8181. Min Act: -0.0001

Data Index: 31988 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8642. Min Act: -0.0001

Data Index: 424792 (C4 (Web Text))

Max Activating Token Index: 237