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

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

Neuron 557 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0553. Min Act: -0.0002

Data Index: 572973 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1087112 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0492. Min Act: -0.0002

Data Index: 640607 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1141819 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1103073 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0446. Min Act: -0.0002

Data Index: 153589 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0463. Min Act: -0.0002

Data Index: 690709 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1154728 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0450. Min Act: -0.0002

Data Index: 263860 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1090309 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1086042 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0444. Min Act: -0.0002

Data Index: 156892 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1105204 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0433. Min Act: -0.0002

Data Index: 123911 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0424. Min Act: -0.0002

Data Index: 315608 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1188049 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1144573 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0428. Min Act: -0.0002

Data Index: 300826 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1065751 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0396. Min Act: -0.0002

Data Index: 676523 (C4 (Web Text))

Max Activating Token Index: 1005