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

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

Neuron 4356 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.4132. Min Act: -0.0000

Data Index: 523665 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1462327 (Python Code)

Max Activating Token Index: 261

Text #2

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2986. Min Act: -0.0000

Data Index: 758089 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2882. Min Act: -0.0000

Data Index: 591606 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1004687 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3053. Min Act: -0.0000

Data Index: 311876 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1628777 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1368728 (Python Code)

Max Activating Token Index: 454

Text #8

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2814. Min Act: -0.0000

Data Index: 353831 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1259200 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2275. Min Act: -0.0000

Data Index: 123584 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2630. Min Act: -0.0000

Data Index: 502283 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2504. Min Act: -0.0000

Data Index: 700996 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1050659 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2570. Min Act: -0.0000

Data Index: 369414 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1127191 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1592590 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1429949 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2581. Min Act: -0.0000

Data Index: 99841 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1362124 (Python Code)

Max Activating Token Index: 335