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

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

Neuron 2016 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.4243. Min Act: -0.0001

Data Index: 654944 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3517. Min Act: -0.0001

Data Index: 791334 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3762. Min Act: -0.0001

Data Index: 220176 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3474. Min Act: -0.0001

Data Index: 827879 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3351. Min Act: -0.0001

Data Index: 883183 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3654. Min Act: -0.0001

Data Index: 950049 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3700. Min Act: -0.0001

Data Index: 329288 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3457. Min Act: -0.0001

Data Index: 143595 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3437. Min Act: -0.0001

Data Index: 451819 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3422. Min Act: -0.0001

Data Index: 458674 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3572. Min Act: -0.0001

Data Index: 15700 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3209. Min Act: -0.0001

Data Index: 1311734 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3337. Min Act: -0.0001

Data Index: 410726 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3303. Min Act: -0.0001

Data Index: 820107 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3210. Min Act: -0.0001

Data Index: 661453 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1240377 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3140. Min Act: -0.0001

Data Index: 885737 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3353. Min Act: -0.0001

Data Index: 377176 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3181. Min Act: -0.0001

Data Index: 693219 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3270. Min Act: -0.0001

Data Index: 423552 (C4 (Web Text))

Max Activating Token Index: 838