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

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

Neuron 1019 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3495. Min Range: -1.3495

Max Act: 1.3261. Min Act: -0.0000

Data Index: 642065 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 1.3495. Min Range: -1.3495

Max Act: 1.3495. Min Act: -0.0000

Data Index: 749913 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 1.3495. Min Range: -1.3495

Max Act: 1.2653. Min Act: -0.0001

Data Index: 434409 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 1.3495. Min Range: -1.3495

Max Act: 1.1202. Min Act: -0.0000

Data Index: 729551 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.3495. Min Range: -1.3495

Max Act: 1.1515. Min Act: -0.0000

Data Index: 790623 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 1.3495. Min Range: -1.3495

Max Act: 1.0663. Min Act: -0.0000

Data Index: 591203 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.3495. Min Range: -1.3495

Max Act: 1.1038. Min Act: -0.0000

Data Index: 776601 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9987. Min Act: -0.0000

Data Index: 705968 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1305928 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1042617 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9553. Min Act: -0.0000

Data Index: 469211 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1058228 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9394. Min Act: -0.0001

Data Index: 47662 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9860. Min Act: -0.0000

Data Index: 51981 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.3495. Min Range: -1.3495

Max Act: 1.0150. Min Act: -0.0000

Data Index: 944290 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9252. Min Act: -0.0000

Data Index: 672205 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9006. Min Act: -0.0000

Data Index: 961880 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 1.3495. Min Range: -1.3495

Max Act: 1.0745. Min Act: -0.0000

Data Index: 1204453 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9383. Min Act: -0.0000

Data Index: 189329 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.3495. Min Range: -1.3495

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1051824 (C4 (Web Text))

Max Activating Token Index: 685