Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 206 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0003

Data Index: 695715 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0402. Min Act: -0.0003

Data Index: 652141 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0372. Min Act: -0.0003

Data Index: 465576 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0365. Min Act: -0.0004

Data Index: 1004604 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0357. Min Act: -0.0003

Data Index: 102898 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0349. Min Act: -0.0003

Data Index: 634960 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0329. Min Act: -0.0003

Data Index: 463224 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1548625 (Python Code)

Max Activating Token Index: 520

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1590779 (Python Code)

Max Activating Token Index: 223

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1453996 (Python Code)

Max Activating Token Index: 458

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1124650 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1538237 (Python Code)

Max Activating Token Index: 455

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1631384 (Python Code)

Max Activating Token Index: 690

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1347163 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1484403 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0317. Min Act: -0.0003

Data Index: 742509 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1421690 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0298. Min Act: -0.0003

Data Index: 323742 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1576161 (Python Code)

Max Activating Token Index: 355

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1582132 (Python Code)

Max Activating Token Index: 233