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

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

Neuron 5352 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0830. Min Range: -2.0830

Max Act: 2.0830. Min Act: -0.0000

Data Index: 1300956 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.6758. Min Act: -0.0000

Data Index: 848766 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.4038. Min Act: -0.0000

Data Index: 1149583 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.5206. Min Act: -0.0000

Data Index: 55660 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.4529. Min Act: -0.0000

Data Index: 1011489 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.2971. Min Act: -0.0000

Data Index: 679216 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.3719. Min Act: -0.0000

Data Index: 1341844 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.2554. Min Act: -0.0000

Data Index: 426349 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.3096. Min Act: -0.0000

Data Index: 89658 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.4204. Min Act: -0.0000

Data Index: 648196 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1307639 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.2476. Min Act: -0.0000

Data Index: 1198202 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.3083. Min Act: -0.0000

Data Index: 60017 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.1378. Min Act: -0.0000

Data Index: 801600 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.1026. Min Act: -0.0000

Data Index: 664278 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.1329. Min Act: -0.0000

Data Index: 756661 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.1576. Min Act: -0.0000

Data Index: 81479 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.0475. Min Act: -0.0000

Data Index: 220458 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 2.0830. Min Range: -2.0830

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1305584 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 2.0830. Min Range: -2.0830

Max Act: 0.9633. Min Act: -0.0000

Data Index: 768881 (C4 (Web Text))

Max Activating Token Index: 161