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

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

Neuron 3352 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: 4.4354. Min Range: -4.4354

Max Act: 4.4354. Min Act: -0.0001

Data Index: 789688 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.1863. Min Act: -0.0001

Data Index: 40537 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.9644. Min Act: -0.0001

Data Index: 113810 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.5657. Min Act: -0.0001

Data Index: 381734 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.5067. Min Act: -0.0001

Data Index: 1238096 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.5019. Min Act: -0.0001

Data Index: 718027 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.4821. Min Act: -0.0001

Data Index: 729828 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.2487. Min Act: -0.0001

Data Index: 20930 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.2102. Min Act: -0.0001

Data Index: 1257596 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.1786. Min Act: -0.0000

Data Index: 989441 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.2958. Min Act: -0.0001

Data Index: 1334577 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.2483. Min Act: -0.0001

Data Index: 911669 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.0799. Min Act: -0.0001

Data Index: 120151 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.0444. Min Act: -0.0001

Data Index: 1299936 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 4.4354. Min Range: -4.4354

Max Act: 2.9937. Min Act: -0.0001

Data Index: 1261557 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.1138. Min Act: -0.0001

Data Index: 1319727 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.0782. Min Act: -0.0000

Data Index: 227207 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.0894. Min Act: -0.0001

Data Index: 1303787 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.0655. Min Act: -0.0001

Data Index: 1161491 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.0472. Min Act: -0.0001

Data Index: 490418 (C4 (Web Text))

Max Activating Token Index: 32