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

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

Neuron 3008 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3570. Min Act: -0.0000

Data Index: 530920 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1295145 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1209196 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1948. Min Act: -0.0000

Data Index: 793718 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1434. Min Act: -0.0000

Data Index: 190847 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1381. Min Act: -0.0000

Data Index: 1324519 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1588. Min Act: -0.0000

Data Index: 394208 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0916. Min Act: -0.0000

Data Index: 748509 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9986. Min Act: -0.0000

Data Index: 548133 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9886. Min Act: -0.0000

Data Index: 651911 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0097. Min Act: -0.0000

Data Index: 210122 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1110367 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0551. Min Act: -0.0000

Data Index: 367138 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1294596 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9999. Min Act: -0.0000

Data Index: 827135 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.8429. Min Act: -0.0000

Data Index: 4339 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.8964. Min Act: -0.0000

Data Index: 699388 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9399. Min Act: 0.0000

Data Index: 835113 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9395. Min Act: -0.0000

Data Index: 942766 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1033162 (C4 (Web Text))

Max Activating Token Index: 778