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

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

Neuron 4334 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1292771 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0516. Min Act: -0.0002

Data Index: 421518 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0493. Min Act: -0.0002

Data Index: 440580 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1235557 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0436. Min Act: -0.0002

Data Index: 394261 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0469. Min Act: -0.0002

Data Index: 584793 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1038643 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1214139 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0429. Min Act: -0.0003

Data Index: 835454 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1282949 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0420. Min Act: -0.0002

Data Index: 606547 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1208797 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1326903 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0410. Min Act: -0.0002

Data Index: 856871 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1129024 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1240369 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0434. Min Act: -0.0003

Data Index: 949845 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0389. Min Act: -0.0003

Data Index: 899231 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0391. Min Act: -0.0002

Data Index: 974300 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0411. Min Act: -0.0002

Data Index: 502531 (C4 (Web Text))

Max Activating Token Index: 336