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

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

Neuron 120 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: 1.1742. Min Range: -1.1742

Max Act: 1.1742. Min Act: 0.0000

Data Index: 1171901 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.9067. Min Act: -0.0000

Data Index: 471230 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.1742. Min Range: -1.1742

Max Act: 1.0438. Min Act: -0.0000

Data Index: 257957 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8884. Min Act: -0.0000

Data Index: 194433 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.9475. Min Act: 0.0001

Data Index: 787115 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8681. Min Act: -0.0000

Data Index: 994135 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8597. Min Act: -0.0000

Data Index: 427551 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8249. Min Act: -0.0000

Data Index: 837516 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.7980. Min Act: -0.0000

Data Index: 751619 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1221586 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.9014. Min Act: -0.0000

Data Index: 802311 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1080358 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1193644 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1539727 (Python Code)

Max Activating Token Index: 789

Text #14

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8893. Min Act: -0.0000

Data Index: 219011 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8308. Min Act: -0.0000

Data Index: 504777 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.7547. Min Act: -0.0000

Data Index: 803301 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1083222 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8059. Min Act: -0.0000

Data Index: 825840 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.7913. Min Act: -0.0000

Data Index: 88620 (C4 (Web Text))

Max Activating Token Index: 608