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

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

Neuron 3623 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: 3.0391. Min Range: -3.0391

Max Act: 3.0391. Min Act: -0.0000

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 3.0391. Min Range: -3.0391

Max Act: 2.7104. Min Act: -0.0000

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 3.0391. Min Range: -3.0391

Max Act: 2.4814. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.7290. Min Act: -0.0001

Data Index: 786701 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.4146. Min Act: -0.0001

Data Index: 155614 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.3731. Min Act: -0.0000

Data Index: 894827 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.3665. Min Act: -0.0001

Data Index: 153016 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.3497. Min Act: -0.0001

Data Index: 1103541 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.3045. Min Act: -0.0001

Data Index: 1136417 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.2871. Min Act: -0.0001

Data Index: 894373 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.4133. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.2424. Min Act: -0.0001

Data Index: 18350 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.2435. Min Act: -0.0001

Data Index: 770791 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.1757. Min Act: -0.0001

Data Index: 69771 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.1291. Min Act: -0.0001

Data Index: 1302137 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.1814. Min Act: -0.0001

Data Index: 1335872 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.2603. Min Act: -0.0001

Data Index: 1187222 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.2697. Min Act: -0.0001

Data Index: 285013 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.1844. Min Act: -0.0001

Data Index: 1269789 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 3.0391. Min Range: -3.0391

Max Act: 1.0778. Min Act: -0.0001

Data Index: 1246998 (C4 (Web Text))

Max Activating Token Index: 750