Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1078 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.3339. Min Act: -0.0001

Data Index: 748087 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.0977. Min Act: -0.0001

Data Index: 718086 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.0864. Min Act: -0.0001

Data Index: 640212 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9927. Min Act: -0.0001

Data Index: 215817 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.8185. Min Act: -0.0001

Data Index: 337493 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.8541. Min Act: -0.0001

Data Index: 773134 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.8469. Min Act: -0.0001

Data Index: 1079792 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.7848. Min Act: -0.0001

Data Index: 236468 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.7769. Min Act: -0.0001

Data Index: 978222 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.8037. Min Act: -0.0001

Data Index: 374425 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.7525. Min Act: -0.0001

Data Index: 407939 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.7762. Min Act: -0.0001

Data Index: 297412 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.7642. Min Act: -0.0001

Data Index: 195443 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.7839. Min Act: -0.0001

Data Index: 476957 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1185005 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.8582. Min Act: -0.0001

Data Index: 279829 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.7711. Min Act: -0.0001

Data Index: 1179837 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.8271. Min Act: -0.0001

Data Index: 833106 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.8185. Min Act: -0.0001

Data Index: 1130056 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.7907. Min Act: -0.0001

Data Index: 500046 (C4 (Web Text))

Max Activating Token Index: 405