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

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

Neuron 3443 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2186. Min Act: -0.0000

Data Index: 784330 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1310770 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2074. Min Act: -0.0000

Data Index: 7552 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1802. Min Act: 0.0000

Data Index: 1328729 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1853. Min Act: -0.0000

Data Index: 235698 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1732. Min Act: 0.0000

Data Index: 466947 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1046276 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1758. Min Act: 0.0000

Data Index: 448206 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1740. Min Act: -0.0000

Data Index: 644547 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1649354 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1544. Min Act: -0.0000

Data Index: 889733 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1685. Min Act: -0.0000

Data Index: 293458 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1454515 (Python Code)

Max Activating Token Index: 966

Text #13

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1644. Min Act: -0.0000

Data Index: 878880 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1465729 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1450. Min Act: -0.0000

Data Index: 633854 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1394. Min Act: 0.0000

Data Index: 1145100 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1577492 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1297440 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 132