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

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

Neuron 634 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: 0.0708. Min Range: -0.0708

Max Act: 0.0694. Min Act: -0.0001

Data Index: 621312 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1036097 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0539. Min Act: -0.0001

Data Index: 319661 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1356263 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0645. Min Act: -0.0001

Data Index: 623844 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0581. Min Act: -0.0001

Data Index: 326874 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0620. Min Act: -0.0001

Data Index: 376826 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1191233 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0527. Min Act: -0.0001

Data Index: 887963 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0449. Min Act: -0.0001

Data Index: 355384 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1110992 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0528. Min Act: -0.0001

Data Index: 199736 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0530. Min Act: -0.0001

Data Index: 848995 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0524. Min Act: -0.0001

Data Index: 114573 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0534. Min Act: -0.0001

Data Index: 809020 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0464. Min Act: -0.0001

Data Index: 534629 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0500. Min Act: -0.0001

Data Index: 361651 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0469. Min Act: -0.0001

Data Index: 553963 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0540. Min Act: -0.0001

Data Index: 774548 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1226855 (C4 (Web Text))

Max Activating Token Index: 622