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

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

Neuron 2161 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1811. Min Act: 0.0000

Data Index: 655538 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1738. Min Act: -0.0001

Data Index: 484393 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1633. Min Act: -0.0001

Data Index: 85154 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1774. Min Act: -0.0001

Data Index: 936331 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1290745 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1638. Min Act: -0.0001

Data Index: 257020 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1248128 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1549. Min Act: -0.0001

Data Index: 999897 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1591. Min Act: -0.0001

Data Index: 384606 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1467. Min Act: -0.0001

Data Index: 819240 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1499. Min Act: -0.0001

Data Index: 936100 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1567. Min Act: -0.0001

Data Index: 494348 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1444. Min Act: -0.0001

Data Index: 438678 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1506. Min Act: -0.0001

Data Index: 204646 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1556. Min Act: -0.0001

Data Index: 65759 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1504. Min Act: -0.0001

Data Index: 466413 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1440. Min Act: -0.0001

Data Index: 987545 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1320324 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1540. Min Act: -0.0001

Data Index: 423295 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1469. Min Act: -0.0001

Data Index: 282924 (C4 (Web Text))

Max Activating Token Index: 493