Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2281 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5606. Min Range: -1.5606

Max Act: 1.5606. Min Act: -0.0000

Data Index: 1273153 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 1.5606. Min Range: -1.5606

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1149366 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 1.5606. Min Range: -1.5606

Max Act: 1.3070. Min Act: -0.0000

Data Index: 510752 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 1.5606. Min Range: -1.5606

Max Act: 1.2076. Min Act: -0.0000

Data Index: 19485 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 1.5606. Min Range: -1.5606

Max Act: 1.2291. Min Act: -0.0000

Data Index: 546745 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 1.5606. Min Range: -1.5606

Max Act: 1.1527. Min Act: -0.0000

Data Index: 568547 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 1.5606. Min Range: -1.5606

Max Act: 1.1055. Min Act: -0.0000

Data Index: 624741 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 1.5606. Min Range: -1.5606

Max Act: 1.1582. Min Act: -0.0000

Data Index: 1118990 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 1.5606. Min Range: -1.5606

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1067547 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 1.5606. Min Range: -1.5606

Max Act: 1.0704. Min Act: -0.0000

Data Index: 908133 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.5606. Min Range: -1.5606

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1261447 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 1.5606. Min Range: -1.5606

Max Act: 0.9685. Min Act: -0.0000

Data Index: 1098191 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.5606. Min Range: -1.5606

Max Act: 0.9094. Min Act: -0.0000

Data Index: 495296 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.5606. Min Range: -1.5606

Max Act: 0.9546. Min Act: -0.0000

Data Index: 102751 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.5606. Min Range: -1.5606

Max Act: 0.9730. Min Act: -0.0000

Data Index: 65195 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.5606. Min Range: -1.5606

Max Act: 0.9530. Min Act: -0.0000

Data Index: 18068 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 1.5606. Min Range: -1.5606

Max Act: 0.9631. Min Act: -0.0000

Data Index: 348824 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.5606. Min Range: -1.5606

Max Act: 0.9326. Min Act: -0.0000

Data Index: 154334 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 1.5606. Min Range: -1.5606

Max Act: 0.8484. Min Act: -0.0000

Data Index: 599038 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 1.5606. Min Range: -1.5606

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1148530 (C4 (Web Text))

Max Activating Token Index: 370