Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3507 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.8254. Min Act: -0.0000

Data Index: 789517 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5852. Min Act: -0.0000

Data Index: 934109 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.4743. Min Act: -0.0000

Data Index: 754024 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.3966. Min Act: -0.0000

Data Index: 1251414 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.3458. Min Act: -0.0000

Data Index: 274398 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.2438. Min Act: -0.0000

Data Index: 176222 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.1367. Min Act: -0.0000

Data Index: 564142 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.1298. Min Act: -0.0000

Data Index: 920742 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.1042. Min Act: -0.0000

Data Index: 575864 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.1061. Min Act: -0.0000

Data Index: 110754 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.0627. Min Act: -0.0000

Data Index: 436042 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.9043. Min Act: -0.0000

Data Index: 937674 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.9201. Min Act: -0.0000

Data Index: 658663 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.0446. Min Act: -0.0000

Data Index: 1332551 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.0216. Min Act: -0.0000

Data Index: 275030 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.8796. Min Act: -0.0000

Data Index: 1305835 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.0106. Min Act: -0.0000

Data Index: 137708 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.9938. Min Act: -0.0000

Data Index: 156502 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.8306. Min Act: -0.0000

Data Index: 1257176 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.9516. Min Act: -0.0000

Data Index: 100395 (C4 (Web Text))

Max Activating Token Index: 422