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

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

Neuron 2869 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9582. Min Range: -3.9582

Max Act: 3.9582. Min Act: -0.0001

Data Index: 910777 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 3.9582. Min Range: -3.9582

Max Act: 3.7012. Min Act: -0.0001

Data Index: 668074 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 3.9582. Min Range: -3.9582

Max Act: 3.4542. Min Act: -0.0001

Data Index: 824816 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 3.9582. Min Range: -3.9582

Max Act: 3.1383. Min Act: -0.0001

Data Index: 1074908 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 3.9582. Min Range: -3.9582

Max Act: 3.3035. Min Act: -0.0001

Data Index: 25647 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 3.9582. Min Range: -3.9582

Max Act: 3.1635. Min Act: -0.0001

Data Index: 860600 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 3.9582. Min Range: -3.9582

Max Act: 3.1067. Min Act: -0.0001

Data Index: 330636 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 3.9582. Min Range: -3.9582

Max Act: 3.1157. Min Act: -0.0001

Data Index: 657883 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.8676. Min Act: -0.0001

Data Index: 619623 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.9675. Min Act: -0.0001

Data Index: 1310790 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.9523. Min Act: -0.0001

Data Index: 1006532 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.9257. Min Act: -0.0001

Data Index: 1096066 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.7180. Min Act: -0.0001

Data Index: 276819 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 3.9582. Min Range: -3.9582

Max Act: 3.1330. Min Act: -0.0001

Data Index: 287205 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.8255. Min Act: -0.0001

Data Index: 71417 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.9940. Min Act: -0.0001

Data Index: 464181 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.7454. Min Act: -0.0001

Data Index: 946940 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.6672. Min Act: -0.0001

Data Index: 344005 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.5642. Min Act: -0.0001

Data Index: 1108982 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 3.9582. Min Range: -3.9582

Max Act: 2.7572. Min Act: -0.0001

Data Index: 117581 (C4 (Web Text))

Max Activating Token Index: 57