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

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

Neuron 3573 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2339. Min Act: -0.0000

Data Index: 910098 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2093. Min Act: -0.0000

Data Index: 883528 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2060. Min Act: -0.0001

Data Index: 1306512 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1203868 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1095089 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1947. Min Act: -0.0001

Data Index: 922064 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1011677 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1779. Min Act: -0.0001

Data Index: 594264 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1611. Min Act: -0.0000

Data Index: 671349 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1653. Min Act: -0.0000

Data Index: 804705 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1765. Min Act: -0.0001

Data Index: 1119586 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1052433 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1596. Min Act: -0.0000

Data Index: 344785 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1467. Min Act: -0.0001

Data Index: 621447 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1680. Min Act: -0.0000

Data Index: 474958 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1560. Min Act: -0.0001

Data Index: 877152 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1557. Min Act: -0.0000

Data Index: 421464 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1542. Min Act: -0.0000

Data Index: 947872 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1518. Min Act: -0.0000

Data Index: 935638 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1682. Min Act: -0.0001

Data Index: 692330 (C4 (Web Text))

Max Activating Token Index: 71