Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1390 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8624. Min Act: -0.0001

Data Index: 256831 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8301. Min Act: -0.0001

Data Index: 481986 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7927. Min Act: -0.0001

Data Index: 313768 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7814. Min Act: -0.0001

Data Index: 649080 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7468. Min Act: -0.0001

Data Index: 529086 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7635. Min Act: -0.0001

Data Index: 592242 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8510. Min Act: -0.0001

Data Index: 606250 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7513. Min Act: -0.0001

Data Index: 484964 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7267. Min Act: -0.0001

Data Index: 321755 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7451. Min Act: -0.0001

Data Index: 363855 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7362. Min Act: -0.0001

Data Index: 1080283 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8042. Min Act: -0.0001

Data Index: 796762 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7528. Min Act: -0.0001

Data Index: 726042 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7660. Min Act: -0.0001

Data Index: 588866 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7702. Min Act: -0.0001

Data Index: 966587 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7427. Min Act: -0.0001

Data Index: 1232592 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7658. Min Act: -0.0001

Data Index: 997370 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6965. Min Act: -0.0001

Data Index: 945681 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6932. Min Act: -0.0001

Data Index: 1123338 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7333. Min Act: -0.0001

Data Index: 422779 (C4 (Web Text))

Max Activating Token Index: 734