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

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

Neuron 3017 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: 0.6781. Min Range: -0.6781

Max Act: 0.6781. Min Act: -0.0001

Data Index: 1134596 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6585. Min Act: -0.0001

Data Index: 528306 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6537. Min Act: -0.0001

Data Index: 1000725 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6025. Min Act: -0.0001

Data Index: 1288745 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5388. Min Act: -0.0001

Data Index: 215618 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5306. Min Act: -0.0001

Data Index: 1258918 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5984. Min Act: -0.0001

Data Index: 389558 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4463. Min Act: -0.0001

Data Index: 1245610 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5024. Min Act: -0.0001

Data Index: 258284 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4798. Min Act: -0.0001

Data Index: 648534 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4465. Min Act: -0.0001

Data Index: 625906 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4657. Min Act: -0.0001

Data Index: 1237779 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4906. Min Act: -0.0001

Data Index: 941372 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4520. Min Act: -0.0001

Data Index: 99004 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4935. Min Act: -0.0001

Data Index: 819180 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4579. Min Act: -0.0001

Data Index: 942297 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.3677. Min Act: -0.0001

Data Index: 1139721 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4274. Min Act: -0.0001

Data Index: 246274 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4113. Min Act: -0.0001

Data Index: 277001 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4289. Min Act: -0.0001

Data Index: 567683 (C4 (Web Text))

Max Activating Token Index: 889