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

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

Neuron 2916 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1102832 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1993. Min Act: -0.0001

Data Index: 502297 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1876. Min Act: -0.0001

Data Index: 246612 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1844. Min Act: -0.0001

Data Index: 779254 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1290941 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1437. Min Act: -0.0001

Data Index: 120458 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1725. Min Act: -0.0001

Data Index: 507257 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1667. Min Act: -0.0001

Data Index: 247083 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1456. Min Act: -0.0001

Data Index: 185284 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1015736 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1431. Min Act: -0.0001

Data Index: 57938 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1308852 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1150622 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1529. Min Act: -0.0001

Data Index: 312904 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1459. Min Act: -0.0001

Data Index: 158471 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1404. Min Act: -0.0001

Data Index: 975903 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1035592 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1484. Min Act: -0.0001

Data Index: 930792 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1138619 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1447. Min Act: -0.0001

Data Index: 317370 (C4 (Web Text))

Max Activating Token Index: 255