Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1320 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.6651. Min Act: -0.0001

Data Index: 508099 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5841. Min Act: -0.0001

Data Index: 362493 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5145. Min Act: -0.0001

Data Index: 576870 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5457. Min Act: -0.0001

Data Index: 952862 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4947. Min Act: -0.0001

Data Index: 219156 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5056. Min Act: -0.0001

Data Index: 55038 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5316. Min Act: -0.0000

Data Index: 51336 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4910. Min Act: -0.0001

Data Index: 463016 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4822. Min Act: -0.0001

Data Index: 613267 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4865. Min Act: -0.0001

Data Index: 620257 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4535. Min Act: -0.0001

Data Index: 34644 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4442. Min Act: -0.0001

Data Index: 417475 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4473. Min Act: -0.0001

Data Index: 337099 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4191. Min Act: -0.0001

Data Index: 382792 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4476. Min Act: -0.0001

Data Index: 695830 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4351. Min Act: -0.0001

Data Index: 804268 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1240498 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4434. Min Act: -0.0001

Data Index: 155915 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4359. Min Act: -0.0001

Data Index: 345263 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4343. Min Act: -0.0001

Data Index: 552833 (C4 (Web Text))

Max Activating Token Index: 136