Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5135 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1217270 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0706. Min Act: -0.0000

Data Index: 208572 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0678. Min Act: -0.0000

Data Index: 127141 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0642. Min Act: -0.0000

Data Index: 615274 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0649. Min Act: -0.0000

Data Index: 920054 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1160654 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0650. Min Act: -0.0000

Data Index: 826625 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1166210 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0598. Min Act: -0.0000

Data Index: 476379 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0560. Min Act: -0.0000

Data Index: 447289 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0578. Min Act: -0.0000

Data Index: 439858 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1027739 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0541. Min Act: -0.0000

Data Index: 655352 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1347299 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0519. Min Act: -0.0000

Data Index: 946250 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0554. Min Act: -0.0000

Data Index: 176584 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0532. Min Act: -0.0000

Data Index: 198730 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0545. Min Act: 0.0000

Data Index: 411857 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0545. Min Act: -0.0000

Data Index: 47967 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0544. Min Act: -0.0000

Data Index: 285062 (C4 (Web Text))

Max Activating Token Index: 572