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

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

Neuron 5180 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8408. Min Range: -6.8408

Max Act: 6.8408. Min Act: -0.0000

Data Index: 252752 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 6.8408. Min Range: -6.8408

Max Act: 6.2782. Min Act: -0.0000

Data Index: 242184 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 6.8408. Min Range: -6.8408

Max Act: 6.1932. Min Act: -0.0001

Data Index: 755763 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 6.8408. Min Range: -6.8408

Max Act: 6.1747. Min Act: -0.0001

Data Index: 919331 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 6.8408. Min Range: -6.8408

Max Act: 6.0249. Min Act: -0.0001

Data Index: 794921 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 6.8408. Min Range: -6.8408

Max Act: 5.5410. Min Act: -0.0001

Data Index: 824736 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 6.8408. Min Range: -6.8408

Max Act: 5.1494. Min Act: -0.0001

Data Index: 1016023 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 6.8408. Min Range: -6.8408

Max Act: 4.7221. Min Act: -0.0001

Data Index: 1035745 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 6.8408. Min Range: -6.8408

Max Act: 5.0485. Min Act: -0.0001

Data Index: 681094 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 6.8408. Min Range: -6.8408

Max Act: 5.3387. Min Act: -0.0001

Data Index: 854653 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 6.8408. Min Range: -6.8408

Max Act: 5.0340. Min Act: -0.0001

Data Index: 310619 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 6.8408. Min Range: -6.8408

Max Act: 4.6508. Min Act: -0.0000

Data Index: 293914 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 6.8408. Min Range: -6.8408

Max Act: 4.0811. Min Act: -0.0001

Data Index: 1237556 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 6.8408. Min Range: -6.8408

Max Act: 4.7603. Min Act: -0.0000

Data Index: 16718 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 6.8408. Min Range: -6.8408

Max Act: 4.6888. Min Act: -0.0000

Data Index: 385384 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 6.8408. Min Range: -6.8408

Max Act: 3.9664. Min Act: -0.0001

Data Index: 703920 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 6.8408. Min Range: -6.8408

Max Act: 4.5419. Min Act: -0.0001

Data Index: 740060 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 6.8408. Min Range: -6.8408

Max Act: 4.0707. Min Act: -0.0001

Data Index: 981623 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 6.8408. Min Range: -6.8408

Max Act: 4.7245. Min Act: -0.0001

Data Index: 1024241 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 6.8408. Min Range: -6.8408

Max Act: 4.5499. Min Act: -0.0000

Data Index: 876592 (C4 (Web Text))

Max Activating Token Index: 825