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

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

Neuron 2804 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.7696. Min Act: -0.0001

Data Index: 365942 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.7600. Min Act: -0.0001

Data Index: 497293 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6920. Min Act: -0.0001

Data Index: 738584 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6806. Min Act: -0.0001

Data Index: 870729 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6940. Min Act: -0.0001

Data Index: 221508 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6569. Min Act: -0.0001

Data Index: 741521 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.7087. Min Act: -0.0001

Data Index: 449878 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6712. Min Act: -0.0001

Data Index: 667219 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6721. Min Act: -0.0001

Data Index: 80017 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6656. Min Act: -0.0001

Data Index: 516862 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5677. Min Act: -0.0001

Data Index: 1219853 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6069. Min Act: -0.0001

Data Index: 730982 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6164. Min Act: -0.0001

Data Index: 158610 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6719. Min Act: -0.0001

Data Index: 838303 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6464. Min Act: -0.0001

Data Index: 338893 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6092. Min Act: -0.0001

Data Index: 1173320 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6291. Min Act: -0.0001

Data Index: 676217 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6231. Min Act: -0.0001

Data Index: 1031513 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6236. Min Act: -0.0001

Data Index: 559875 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6071. Min Act: -0.0001

Data Index: 412603 (C4 (Web Text))

Max Activating Token Index: 902