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

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

Neuron 2014 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1269071 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1303499 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1041105 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1051. Min Act: -0.0001

Data Index: 474011 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0801. Min Act: -0.0001

Data Index: 227753 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0711. Min Act: -0.0001

Data Index: 301885 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0624. Min Act: -0.0001

Data Index: 373077 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1174708 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0593. Min Act: -0.0001

Data Index: 378949 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1326037 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0575. Min Act: -0.0001

Data Index: 907162 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0559. Min Act: -0.0001

Data Index: 105781 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1149393 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0496. Min Act: -0.0001

Data Index: 900025 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1332894 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0530. Min Act: -0.0001

Data Index: 843793 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1596269 (Python Code)

Max Activating Token Index: 613

Text #17

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0464. Min Act: -0.0001

Data Index: 996744 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1399796 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0497. Min Act: -0.0001

Data Index: 86557 (C4 (Web Text))

Max Activating Token Index: 965