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

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

Neuron 78 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: 0.3848. Min Range: -0.3848

Max Act: 0.3848. Min Act: -0.0000

Data Index: 242137 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3493. Min Act: -0.0000

Data Index: 666597 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1249192 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3009. Min Act: -0.0000

Data Index: 129798 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1209800 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3191. Min Act: -0.0000

Data Index: 535511 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2792. Min Act: -0.0000

Data Index: 456830 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3054. Min Act: -0.0000

Data Index: 817158 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1301792 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1348421 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2922. Min Act: -0.0000

Data Index: 467171 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2891. Min Act: -0.0000

Data Index: 636909 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1194951 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1228874 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2639. Min Act: -0.0000

Data Index: 76291 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1059694 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2583. Min Act: -0.0000

Data Index: 363660 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1163193 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2589. Min Act: -0.0000

Data Index: 676384 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2664. Min Act: -0.0000

Data Index: 580790 (C4 (Web Text))

Max Activating Token Index: 856