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

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

Neuron 3844 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.3123. Min Act: -0.0001

Data Index: 386192 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2923. Min Act: -0.0001

Data Index: 1148809 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1154234 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.3033. Min Act: -0.0001

Data Index: 298017 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2803. Min Act: -0.0001

Data Index: 844025 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2687. Min Act: -0.0001

Data Index: 1280315 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2707. Min Act: -0.0001

Data Index: 656153 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2605. Min Act: -0.0001

Data Index: 807525 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1042469 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1680. Min Act: -0.0001

Data Index: 267763 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1602. Min Act: -0.0001

Data Index: 548175 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1642. Min Act: -0.0000

Data Index: 950934 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1852. Min Act: -0.0001

Data Index: 632537 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1514. Min Act: -0.0000

Data Index: 68671 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1503. Min Act: -0.0000

Data Index: 648453 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1294607 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1536. Min Act: -0.0000

Data Index: 396747 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1319770 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1542. Min Act: -0.0000

Data Index: 908723 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1568. Min Act: -0.0001

Data Index: 954418 (C4 (Web Text))

Max Activating Token Index: 230