Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3028 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.6319. Min Act: -0.0001

Data Index: 387189 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.5423. Min Act: -0.0001

Data Index: 570467 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.5636. Min Act: -0.0001

Data Index: 536863 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.5574. Min Act: -0.0001

Data Index: 1243779 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.5444. Min Act: -0.0001

Data Index: 192625 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.5016. Min Act: -0.0001

Data Index: 863609 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.5134. Min Act: -0.0001

Data Index: 651419 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4916. Min Act: -0.0001

Data Index: 273799 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4858. Min Act: -0.0001

Data Index: 744534 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4858. Min Act: -0.0001

Data Index: 1235625 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4806. Min Act: -0.0001

Data Index: 987325 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4648. Min Act: -0.0001

Data Index: 391714 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4763. Min Act: -0.0001

Data Index: 1248849 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4794. Min Act: -0.0001

Data Index: 863684 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4792. Min Act: -0.0001

Data Index: 408741 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.5009. Min Act: -0.0001

Data Index: 734606 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4631. Min Act: -0.0001

Data Index: 1155727 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4416. Min Act: -0.0001

Data Index: 12843 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4735. Min Act: -0.0001

Data Index: 328672 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.5328. Min Act: -0.0001

Data Index: 886151 (C4 (Web Text))

Max Activating Token Index: 845