Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1312 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1302. Min Act: -0.0001

Data Index: 855260 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0933. Min Act: -0.0001

Data Index: 1186850 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1052679 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0829. Min Act: -0.0001

Data Index: 699777 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0785. Min Act: -0.0001

Data Index: 280367 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1117489 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0764. Min Act: -0.0001

Data Index: 470213 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0695. Min Act: -0.0001

Data Index: 925306 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1221424 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0687. Min Act: -0.0001

Data Index: 15686 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0676. Min Act: -0.0001

Data Index: 84316 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0645. Min Act: -0.0001

Data Index: 718417 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0683. Min Act: -0.0001

Data Index: 776222 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0644. Min Act: -0.0001

Data Index: 752568 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0613. Min Act: -0.0001

Data Index: 589485 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0622. Min Act: -0.0001

Data Index: 549000 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0615. Min Act: -0.0001

Data Index: 26975 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1420979 (Python Code)

Max Activating Token Index: 448

Text #18

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1057953 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0567. Min Act: -0.0001

Data Index: 428840 (C4 (Web Text))

Max Activating Token Index: 623