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

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

Neuron 3468 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: 0.2632. Min Range: -0.2632

Max Act: 0.2632. Min Act: -0.0000

Data Index: 893845 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2223. Min Act: 0.0000

Data Index: 1090260 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2022. Min Act: -0.0000

Data Index: 710665 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2165. Min Act: -0.0000

Data Index: 860154 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1310235 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2026. Min Act: 0.0001

Data Index: 907900 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1994. Min Act: -0.0000

Data Index: 536574 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1896. Min Act: -0.0000

Data Index: 224866 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1826. Min Act: -0.0001

Data Index: 678896 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1250132 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1782. Min Act: -0.0001

Data Index: 695101 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1736. Min Act: -0.0000

Data Index: 62162 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1828. Min Act: -0.0001

Data Index: 187238 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1297150 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1656. Min Act: -0.0000

Data Index: 580020 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1053868 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1516. Min Act: -0.0000

Data Index: 947922 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1194465 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1199269 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1328771 (C4 (Web Text))

Max Activating Token Index: 794