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

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

Neuron 1417 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.7242. Min Act: -0.0001

Data Index: 1115673 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.6530. Min Act: -0.0001

Data Index: 846556 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.6187. Min Act: -0.0001

Data Index: 195188 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5778. Min Act: -0.0001

Data Index: 680441 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5457. Min Act: -0.0001

Data Index: 583287 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5942. Min Act: -0.0001

Data Index: 50202 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4998. Min Act: -0.0000

Data Index: 850810 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5392. Min Act: -0.0001

Data Index: 1330271 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5295. Min Act: -0.0001

Data Index: 872930 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5010. Min Act: -0.0001

Data Index: 295660 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5216. Min Act: -0.0000

Data Index: 769706 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1323257 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4557. Min Act: -0.0001

Data Index: 1036678 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4555. Min Act: -0.0000

Data Index: 74739 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4672. Min Act: -0.0001

Data Index: 881210 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4776. Min Act: -0.0000

Data Index: 637656 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4340. Min Act: -0.0001

Data Index: 514177 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4449. Min Act: -0.0001

Data Index: 345111 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4468. Min Act: -0.0000

Data Index: 684297 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4475. Min Act: -0.0001

Data Index: 358241 (C4 (Web Text))

Max Activating Token Index: 481