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

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

Neuron 573 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0406. Min Range: -1.0406

Max Act: 1.0406. Min Act: -0.0001

Data Index: 801688 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.0406. Min Range: -1.0406

Max Act: 1.0059. Min Act: -0.0001

Data Index: 496010 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.8795. Min Act: -0.0001

Data Index: 768228 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7493. Min Act: -0.0001

Data Index: 503131 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7484. Min Act: -0.0001

Data Index: 1243465 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7249. Min Act: -0.0001

Data Index: 466145 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7568. Min Act: -0.0001

Data Index: 350981 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7824. Min Act: -0.0001

Data Index: 376350 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6890. Min Act: -0.0001

Data Index: 809485 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7286. Min Act: -0.0001

Data Index: 971883 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6636. Min Act: -0.0001

Data Index: 170806 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6626. Min Act: -0.0001

Data Index: 141190 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6098. Min Act: -0.0001

Data Index: 587249 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6452. Min Act: -0.0001

Data Index: 321292 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6838. Min Act: -0.0001

Data Index: 1246517 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6083. Min Act: -0.0001

Data Index: 826686 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6703. Min Act: -0.0001

Data Index: 230045 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6634. Min Act: -0.0001

Data Index: 103739 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.5721. Min Act: -0.0001

Data Index: 1273629 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.5874. Min Act: -0.0001

Data Index: 783885 (C4 (Web Text))

Max Activating Token Index: 176