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

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

Neuron 3190 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9168. Min Range: -7.9168

Max Act: 7.9168. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 7.9168. Min Range: -7.9168

Max Act: 7.4725. Min Act: -0.0000

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 7.9168. Min Range: -7.9168

Max Act: 7.4736. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 7.9168. Min Range: -7.9168

Max Act: 6.8777. Min Act: -0.0000

Data Index: 805170 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 7.9168. Min Range: -7.9168

Max Act: 6.8870. Min Act: -0.0000

Data Index: 393312 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 7.9168. Min Range: -7.9168

Max Act: 6.4587. Min Act: -0.0000

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 7.9168. Min Range: -7.9168

Max Act: 5.5559. Min Act: -0.0000

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 7.9168. Min Range: -7.9168

Max Act: 5.6638. Min Act: -0.0000

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 7.9168. Min Range: -7.9168

Max Act: 5.5392. Min Act: -0.0000

Data Index: 32052 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 7.9168. Min Range: -7.9168

Max Act: 4.7759. Min Act: -0.0000

Data Index: 22015 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 7.9168. Min Range: -7.9168

Max Act: 4.3634. Min Act: -0.0000

Data Index: 1106114 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 7.9168. Min Range: -7.9168

Max Act: 4.2613. Min Act: -0.0000

Data Index: 627003 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 7.9168. Min Range: -7.9168

Max Act: 4.2942. Min Act: -0.0000

Data Index: 787385 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 7.9168. Min Range: -7.9168

Max Act: 3.8725. Min Act: -0.0000

Data Index: 300954 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 7.9168. Min Range: -7.9168

Max Act: 3.8165. Min Act: -0.0000

Data Index: 1167358 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 7.9168. Min Range: -7.9168

Max Act: 3.1749. Min Act: -0.0000

Data Index: 1016777 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 7.9168. Min Range: -7.9168

Max Act: 3.7838. Min Act: -0.0000

Data Index: 1585512 (Python Code)

Max Activating Token Index: 573

Text #17

Max Range: 7.9168. Min Range: -7.9168

Max Act: 3.8660. Min Act: -0.0000

Data Index: 1533100 (Python Code)

Max Activating Token Index: 677

Text #18

Max Range: 7.9168. Min Range: -7.9168

Max Act: 3.6109. Min Act: -0.0000

Data Index: 956865 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 7.9168. Min Range: -7.9168

Max Act: 3.6849. Min Act: -0.0000

Data Index: 892604 (C4 (Web Text))

Max Activating Token Index: 518