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

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

Neuron 3314 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: 4.4742. Min Range: -4.4742

Max Act: 4.4690. Min Act: -0.0000

Data Index: 238355 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 4.4742. Min Range: -4.4742

Max Act: 4.4742. Min Act: -0.0000

Data Index: 45840 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.7005. Min Act: -0.0000

Data Index: 803162 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.5084. Min Act: -0.0000

Data Index: 826598 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.3128. Min Act: -0.0000

Data Index: 1103985 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.5655. Min Act: -0.0000

Data Index: 630761 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.3497. Min Act: -0.0000

Data Index: 166972 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.2710. Min Act: -0.0000

Data Index: 751695 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.4301. Min Act: -0.0000

Data Index: 83623 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 4.4742. Min Range: -4.4742

Max Act: 2.9855. Min Act: -0.0000

Data Index: 23382 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.2612. Min Act: -0.0000

Data Index: 1340654 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 4.4742. Min Range: -4.4742

Max Act: 2.8085. Min Act: -0.0000

Data Index: 282347 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 4.4742. Min Range: -4.4742

Max Act: 2.7522. Min Act: -0.0000

Data Index: 154689 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.0296. Min Act: -0.0000

Data Index: 163968 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.1471. Min Act: -0.0000

Data Index: 524461 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 4.4742. Min Range: -4.4742

Max Act: 2.9503. Min Act: 0.0002

Data Index: 420503 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 4.4742. Min Range: -4.4742

Max Act: 3.1246. Min Act: -0.0000

Data Index: 328910 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 4.4742. Min Range: -4.4742

Max Act: 2.9082. Min Act: -0.0000

Data Index: 40569 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 4.4742. Min Range: -4.4742

Max Act: 2.8850. Min Act: 0.0000

Data Index: 595697 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 4.4742. Min Range: -4.4742

Max Act: 2.8679. Min Act: 0.0000

Data Index: 493994 (C4 (Web Text))

Max Activating Token Index: 56