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

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

Neuron 3714 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: 0.9736. Min Range: -0.9736

Max Act: 0.9044. Min Act: -0.0001

Data Index: 223091 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.9343. Min Act: -0.0001

Data Index: 948452 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.9736. Min Act: -0.0001

Data Index: 16233 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8051. Min Act: -0.0001

Data Index: 314567 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7867. Min Act: -0.0001

Data Index: 924979 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8020. Min Act: -0.0001

Data Index: 498590 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8665. Min Act: -0.0001

Data Index: 358747 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8869. Min Act: -0.0001

Data Index: 613438 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8572. Min Act: -0.0001

Data Index: 478810 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8213. Min Act: -0.0001

Data Index: 1041104 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7863. Min Act: -0.0001

Data Index: 430411 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8202. Min Act: -0.0001

Data Index: 1074614 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7838. Min Act: -0.0001

Data Index: 937285 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7538. Min Act: -0.0001

Data Index: 388310 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7973. Min Act: -0.0001

Data Index: 755207 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7483. Min Act: -0.0001

Data Index: 17427 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7770. Min Act: -0.0001

Data Index: 1053764 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7633. Min Act: -0.0001

Data Index: 524176 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7610. Min Act: -0.0001

Data Index: 1226678 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7553. Min Act: -0.0001

Data Index: 1143522 (C4 (Web Text))

Max Activating Token Index: 389