Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1055 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0431. Min Act: -0.0003

Data Index: 558588 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0437. Min Act: -0.0003

Data Index: 537306 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0417. Min Act: -0.0003

Data Index: 251444 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0409. Min Act: -0.0003

Data Index: 8374 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0397. Min Act: -0.0003

Data Index: 348734 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0378. Min Act: -0.0003

Data Index: 681898 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0392. Min Act: -0.0003

Data Index: 89622 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0387. Min Act: -0.0003

Data Index: 256947 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1098118 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0370. Min Act: -0.0003

Data Index: 474202 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1299048 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0341. Min Act: -0.0003

Data Index: 726846 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1133360 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0352. Min Act: -0.0003

Data Index: 713868 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1137325 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1077497 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1021496 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0331. Min Act: -0.0003

Data Index: 175668 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0359. Min Act: -0.0003

Data Index: 224805 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0348. Min Act: -0.0003

Data Index: 977406 (C4 (Web Text))

Max Activating Token Index: 345