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

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

Neuron 2056 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: 1.3817. Min Range: -1.3817

Max Act: 1.3817. Min Act: -0.0000

Data Index: 343088 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.3456. Min Act: -0.0001

Data Index: 346435 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.3474. Min Act: -0.0001

Data Index: 434795 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.1745. Min Act: -0.0001

Data Index: 533619 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.2066. Min Act: -0.0000

Data Index: 451771 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.1627. Min Act: -0.0000

Data Index: 318868 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.1558. Min Act: -0.0000

Data Index: 404001 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.1124. Min Act: -0.0000

Data Index: 359912 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.1202. Min Act: -0.0001

Data Index: 423548 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.0424. Min Act: -0.0001

Data Index: 192979 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.0373. Min Act: -0.0001

Data Index: 725259 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.1367. Min Act: -0.0000

Data Index: 321978 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.0962. Min Act: -0.0000

Data Index: 1027547 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.0460. Min Act: -0.0001

Data Index: 137905 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.1825. Min Act: -0.0001

Data Index: 173706 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.0816. Min Act: -0.0001

Data Index: 242125 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.0731. Min Act: -0.0001

Data Index: 694896 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.3817. Min Range: -1.3817

Max Act: 0.9593. Min Act: -0.0001

Data Index: 916447 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 1.3817. Min Range: -1.3817

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1037651 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.3817. Min Range: -1.3817

Max Act: 1.0625. Min Act: -0.0001

Data Index: 1161688 (C4 (Web Text))

Max Activating Token Index: 861