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

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

Neuron 245 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1472. Min Range: -1.1472

Max Act: 1.0841. Min Act: -0.0000

Data Index: 533587 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.1472. Min Range: -1.1472

Max Act: 1.1472. Min Act: -0.0000

Data Index: 260418 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.1472. Min Range: -1.1472

Max Act: 1.0818. Min Act: -0.0000

Data Index: 633961 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 1.1472. Min Range: -1.1472

Max Act: 1.0401. Min Act: -0.0000

Data Index: 1329015 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.1472. Min Range: -1.1472

Max Act: 1.0136. Min Act: -0.0000

Data Index: 741781 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.9551. Min Act: -0.0000

Data Index: 513401 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.9998. Min Act: -0.0000

Data Index: 344792 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1046985 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.9344. Min Act: -0.0000

Data Index: 477335 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.9093. Min Act: -0.0000

Data Index: 216121 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.9021. Min Act: -0.0000

Data Index: 309239 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.8975. Min Act: -0.0000

Data Index: 535812 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1145834 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.8971. Min Act: -0.0000

Data Index: 903569 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1352250 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.8759. Min Act: -0.0000

Data Index: 366137 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.8437. Min Act: -0.0000

Data Index: 69097 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.8303. Min Act: -0.0000

Data Index: 105678 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.8395. Min Act: -0.0000

Data Index: 832078 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 1.1472. Min Range: -1.1472

Max Act: 0.8311. Min Act: -0.0000

Data Index: 541930 (C4 (Web Text))

Max Activating Token Index: 747