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

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

Neuron 2589 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: 0.2339. Min Range: -0.2339

Max Act: 0.2339. Min Act: -0.0001

Data Index: 1114337 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2318. Min Act: -0.0001

Data Index: 1131146 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1916. Min Act: -0.0001

Data Index: 983489 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1886. Min Act: -0.0001

Data Index: 201460 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1874. Min Act: -0.0001

Data Index: 427537 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1892. Min Act: -0.0001

Data Index: 613636 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1494. Min Act: -0.0001

Data Index: 73917 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1064350 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1635. Min Act: -0.0001

Data Index: 456981 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1636262 (Python Code)

Max Activating Token Index: 1016

Text #10

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1545. Min Act: -0.0001

Data Index: 331837 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1178685 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1540. Min Act: -0.0001

Data Index: 603025 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1438. Min Act: -0.0001

Data Index: 297976 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1582. Min Act: -0.0001

Data Index: 198674 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1403. Min Act: -0.0001

Data Index: 902163 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1287. Min Act: -0.0001

Data Index: 81268 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1248758 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1526. Min Act: -0.0001

Data Index: 913330 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1466. Min Act: -0.0001

Data Index: 631250 (C4 (Web Text))

Max Activating Token Index: 1020