Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2075 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1187567 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0629. Min Act: -0.0001

Data Index: 223419 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0620. Min Act: 0.0000

Data Index: 648363 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0623. Min Act: -0.0000

Data Index: 481059 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0557. Min Act: -0.0001

Data Index: 4615 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1208992 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1162381 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0590. Min Act: -0.0001

Data Index: 979671 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0546. Min Act: -0.0001

Data Index: 797951 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0581. Min Act: -0.0001

Data Index: 465405 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0538. Min Act: -0.0001

Data Index: 906844 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1120498 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0538. Min Act: -0.0000

Data Index: 920534 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1148996 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1032177 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0524. Min Act: -0.0001

Data Index: 179764 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1315872 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1289757 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0506. Min Act: -0.0001

Data Index: 608587 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0510. Min Act: -0.0001

Data Index: 774515 (C4 (Web Text))

Max Activating Token Index: 14