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

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

Neuron 3497 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: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1125277 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1367. Min Act: -0.0001

Data Index: 893777 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1510. Min Act: -0.0001

Data Index: 709469 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1117981 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1392. Min Act: -0.0001

Data Index: 117616 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1350823 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1653. Min Act: -0.0001

Data Index: 478193 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1480. Min Act: -0.0001

Data Index: 682297 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1390. Min Act: -0.0001

Data Index: 274802 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1521292 (Python Code)

Max Activating Token Index: 1010

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1205. Min Act: -0.0001

Data Index: 295000 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1202. Min Act: -0.0001

Data Index: 488745 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1227. Min Act: -0.0001

Data Index: 948617 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1131. Min Act: -0.0001

Data Index: 128313 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1073. Min Act: -0.0001

Data Index: 153057 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1278. Min Act: -0.0001

Data Index: 823963 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1182. Min Act: -0.0001

Data Index: 787732 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1002768 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1198. Min Act: -0.0001

Data Index: 117709 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1000. Min Act: -0.0001

Data Index: 427180 (C4 (Web Text))

Max Activating Token Index: 776