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

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

Neuron 4517 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.6576. Min Act: -0.0000

Data Index: 481866 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.5115. Min Act: -0.0000

Data Index: 1353544 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.4813. Min Act: -0.0000

Data Index: 384380 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.4676. Min Act: -0.0000

Data Index: 62552 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.3637. Min Act: -0.0000

Data Index: 967417 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.4229. Min Act: -0.0000

Data Index: 8573 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.2755. Min Act: -0.0000

Data Index: 1111296 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.2003. Min Act: -0.0000

Data Index: 853765 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.2993. Min Act: -0.0000

Data Index: 1274952 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.1328. Min Act: -0.0000

Data Index: 1337124 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 2.6576. Min Range: -2.6576

Max Act: 1.9544. Min Act: -0.0000

Data Index: 297069 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.0636. Min Act: -0.0000

Data Index: 1230588 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.1781. Min Act: -0.0000

Data Index: 412061 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 2.6576. Min Range: -2.6576

Max Act: 2.1254. Min Act: -0.0000

Data Index: 560425 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 2.6576. Min Range: -2.6576

Max Act: 1.9709. Min Act: -0.0000

Data Index: 538598 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 2.6576. Min Range: -2.6576

Max Act: 1.9942. Min Act: -0.0000

Data Index: 1213618 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 2.6576. Min Range: -2.6576

Max Act: 1.9864. Min Act: -0.0000

Data Index: 312344 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 2.6576. Min Range: -2.6576

Max Act: 1.8853. Min Act: -0.0000

Data Index: 40224 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 2.6576. Min Range: -2.6576

Max Act: 1.8828. Min Act: -0.0000

Data Index: 1301335 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 2.6576. Min Range: -2.6576

Max Act: 1.9281. Min Act: -0.0000

Data Index: 801578 (C4 (Web Text))

Max Activating Token Index: 176