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

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

Neuron 3804 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0545. Min Range: -2.0545

Max Act: 2.0545. Min Act: -0.0000

Data Index: 259477 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 2.0545. Min Range: -2.0545

Max Act: 2.0357. Min Act: 0.0000

Data Index: 106306 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.8094. Min Act: -0.0000

Data Index: 594516 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.8462. Min Act: -0.0000

Data Index: 1282979 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.8936. Min Act: -0.0000

Data Index: 776118 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.8418. Min Act: -0.0000

Data Index: 507578 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.8285. Min Act: -0.0000

Data Index: 524936 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.8816. Min Act: -0.0000

Data Index: 1285112 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.7042. Min Act: -0.0000

Data Index: 209537 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.8351. Min Act: -0.0000

Data Index: 367249 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.8813. Min Act: -0.0000

Data Index: 779044 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.7004. Min Act: -0.0000

Data Index: 1136785 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.6125. Min Act: -0.0000

Data Index: 237963 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.8022. Min Act: -0.0000

Data Index: 1171664 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.6582. Min Act: -0.0000

Data Index: 435413 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.7616. Min Act: -0.0000

Data Index: 331175 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.6407. Min Act: -0.0000

Data Index: 989192 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.7323. Min Act: -0.0000

Data Index: 808655 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.7082. Min Act: -0.0000

Data Index: 716656 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 2.0545. Min Range: -2.0545

Max Act: 1.5528. Min Act: -0.0000

Data Index: 603089 (C4 (Web Text))

Max Activating Token Index: 873