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

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

Neuron 914 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2442. Min Range: -5.2442

Max Act: 5.2442. Min Act: -0.0000

Data Index: 1541749 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 5.2442. Min Range: -5.2442

Max Act: 4.5140. Min Act: -0.0000

Data Index: 1600844 (Python Code)

Max Activating Token Index: 745

Text #2

Max Range: 5.2442. Min Range: -5.2442

Max Act: 4.3685. Min Act: -0.0000

Data Index: 1461916 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 5.2442. Min Range: -5.2442

Max Act: 3.9006. Min Act: -0.0000

Data Index: 1483825 (Python Code)

Max Activating Token Index: 559

Text #4

Max Range: 5.2442. Min Range: -5.2442

Max Act: 3.6226. Min Act: -0.0000

Data Index: 274797 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 5.2442. Min Range: -5.2442

Max Act: 3.6120. Min Act: -0.0000

Data Index: 580695 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 5.2442. Min Range: -5.2442

Max Act: 3.6993. Min Act: -0.0000

Data Index: 1636249 (Python Code)

Max Activating Token Index: 107

Text #7

Max Range: 5.2442. Min Range: -5.2442

Max Act: 3.6757. Min Act: -0.0000

Data Index: 627979 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 5.2442. Min Range: -5.2442

Max Act: 3.3038. Min Act: -0.0000

Data Index: 1481735 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 5.2442. Min Range: -5.2442

Max Act: 3.2589. Min Act: -0.0000

Data Index: 1208494 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 5.2442. Min Range: -5.2442

Max Act: 3.1678. Min Act: -0.0000

Data Index: 1058882 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 5.2442. Min Range: -5.2442

Max Act: 3.2827. Min Act: -0.0000

Data Index: 1219954 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 5.2442. Min Range: -5.2442

Max Act: 2.8822. Min Act: -0.0000

Data Index: 820221 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 5.2442. Min Range: -5.2442

Max Act: 2.7245. Min Act: -0.0000

Data Index: 1159756 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 5.2442. Min Range: -5.2442

Max Act: 2.6940. Min Act: -0.0000

Data Index: 84691 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 5.2442. Min Range: -5.2442

Max Act: 2.6632. Min Act: -0.0000

Data Index: 678924 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 5.2442. Min Range: -5.2442

Max Act: 2.5796. Min Act: -0.0000

Data Index: 418015 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 5.2442. Min Range: -5.2442

Max Act: 2.5589. Min Act: -0.0000

Data Index: 476429 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 5.2442. Min Range: -5.2442

Max Act: 2.5129. Min Act: -0.0000

Data Index: 658465 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 5.2442. Min Range: -5.2442

Max Act: 2.4997. Min Act: -0.0000

Data Index: 880796 (C4 (Web Text))

Max Activating Token Index: 157