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

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

Neuron 1575 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: 0.0563. Min Range: -0.0563

Max Act: 0.0563. Min Act: -0.0003

Data Index: 361648 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0382. Min Act: -0.0003

Data Index: 255183 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0316. Min Act: -0.0003

Data Index: 928591 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1098942 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0313. Min Act: -0.0003

Data Index: 411026 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0357. Min Act: -0.0003

Data Index: 927508 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0323. Min Act: -0.0003

Data Index: 322593 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0315. Min Act: -0.0003

Data Index: 211735 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0313. Min Act: -0.0003

Data Index: 801209 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0300. Min Act: -0.0003

Data Index: 769215 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1182503 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1098871 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0320. Min Act: -0.0003

Data Index: 200130 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0321. Min Act: -0.0003

Data Index: 397584 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0302. Min Act: -0.0003

Data Index: 701937 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0291. Min Act: -0.0003

Data Index: 668461 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0300. Min Act: -0.0003

Data Index: 763279 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1073893 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1042569 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1082436 (C4 (Web Text))

Max Activating Token Index: 130