Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 542 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0006

Data Index: 219544 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0568. Min Act: -0.0006

Data Index: 325500 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0562. Min Act: -0.0006

Data Index: 18582 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0557. Min Act: -0.0006

Data Index: 512893 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0557. Min Act: -0.0006

Data Index: 176895 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0546. Min Act: -0.0006

Data Index: 595724 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0520. Min Act: -0.0006

Data Index: 1150317 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0536. Min Act: -0.0006

Data Index: 1289355 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0519. Min Act: -0.0006

Data Index: 1159322 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0532. Min Act: -0.0006

Data Index: 974644 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0532. Min Act: -0.0006

Data Index: 1095413 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0507. Min Act: -0.0006

Data Index: 419403 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0526. Min Act: -0.0006

Data Index: 1229420 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0509. Min Act: -0.0006

Data Index: 87608 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0507. Min Act: -0.0006

Data Index: 104930 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0484. Min Act: -0.0006

Data Index: 730524 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0503. Min Act: -0.0006

Data Index: 946554 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0482. Min Act: -0.0006

Data Index: 1288977 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0483. Min Act: -0.0006

Data Index: 1035369 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0502. Min Act: -0.0006

Data Index: 683357 (C4 (Web Text))

Max Activating Token Index: 49