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

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

Neuron 4618 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0748. Min Range: -2.0748

Max Act: 2.0748. Min Act: -0.0000

Data Index: 485524 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.7160. Min Act: -0.0000

Data Index: 389617 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.7702. Min Act: -0.0000

Data Index: 74258 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.6888. Min Act: -0.0000

Data Index: 1159820 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.5499. Min Act: -0.0000

Data Index: 262227 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.5129. Min Act: -0.0000

Data Index: 1045345 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.5585. Min Act: -0.0000

Data Index: 526834 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.3534. Min Act: -0.0000

Data Index: 1522587 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.4073. Min Act: -0.0000

Data Index: 450487 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.2726. Min Act: -0.0000

Data Index: 891854 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.4056. Min Act: -0.0000

Data Index: 787524 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.3024. Min Act: -0.0000

Data Index: 1105797 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.3491. Min Act: -0.0000

Data Index: 762209 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.3103. Min Act: -0.0000

Data Index: 317851 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.3934. Min Act: -0.0000

Data Index: 990501 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.3831. Min Act: -0.0000

Data Index: 232653 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1340530 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.2782. Min Act: -0.0000

Data Index: 64780 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.3611. Min Act: -0.0000

Data Index: 1587477 (Python Code)

Max Activating Token Index: 540

Text #19

Max Range: 2.0748. Min Range: -2.0748

Max Act: 1.1919. Min Act: -0.0000

Data Index: 1241003 (C4 (Web Text))

Max Activating Token Index: 841