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

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

Neuron 4508 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: 3.0316. Min Range: -3.0316

Max Act: 3.0316. Min Act: -0.0000

Data Index: 316888 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9966. Min Act: -0.0000

Data Index: 445720 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.1850. Min Act: -0.0000

Data Index: 55044 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.9551. Min Act: -0.0000

Data Index: 740023 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.0486. Min Act: -0.0000

Data Index: 410544 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.9252. Min Act: -0.0000

Data Index: 914883 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.0669. Min Act: -0.0000

Data Index: 968372 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.8056. Min Act: -0.0000

Data Index: 87354 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.7970. Min Act: -0.0000

Data Index: 1348315 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.8727. Min Act: -0.0000

Data Index: 140640 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.9211. Min Act: -0.0000

Data Index: 1061335 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.8104. Min Act: -0.0000

Data Index: 125569 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.7544. Min Act: -0.0000

Data Index: 984327 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.7370. Min Act: -0.0000

Data Index: 33045 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.7165. Min Act: -0.0000

Data Index: 730560 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.6161. Min Act: -0.0000

Data Index: 1291716 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.8046. Min Act: -0.0000

Data Index: 295665 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.6909. Min Act: -0.0000

Data Index: 723652 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.5639. Min Act: -0.0000

Data Index: 782879 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 3.0316. Min Range: -3.0316

Max Act: 1.5552. Min Act: -0.0000

Data Index: 1235420 (C4 (Web Text))

Max Activating Token Index: 378