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

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

Neuron 2463 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0003

Data Index: 619833 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0567. Min Act: -0.0003

Data Index: 713036 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1012543 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0559. Min Act: -0.0002

Data Index: 151059 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0559. Min Act: -0.0003

Data Index: 223867 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0571. Min Act: -0.0003

Data Index: 495529 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0545. Min Act: -0.0003

Data Index: 636231 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0520. Min Act: -0.0002

Data Index: 813372 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0514. Min Act: -0.0003

Data Index: 345435 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0500. Min Act: -0.0003

Data Index: 784316 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0483. Min Act: -0.0002

Data Index: 482653 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0475. Min Act: -0.0003

Data Index: 759755 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0484. Min Act: -0.0003

Data Index: 417364 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0466. Min Act: -0.0003

Data Index: 860779 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0462. Min Act: -0.0003

Data Index: 912070 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0455. Min Act: -0.0003

Data Index: 359613 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0459. Min Act: -0.0003

Data Index: 232015 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0469. Min Act: -0.0003

Data Index: 594107 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0457. Min Act: -0.0003

Data Index: 98254 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0453. Min Act: -0.0002

Data Index: 55728 (C4 (Web Text))

Max Activating Token Index: 243