Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1325 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0280. Min Act: -0.0005

Data Index: 682443 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0273. Min Act: -0.0005

Data Index: 294169 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0005

Data Index: 892922 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0273. Min Act: -0.0005

Data Index: 143725 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1339654 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0273. Min Act: -0.0005

Data Index: 1376445 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0273. Min Act: -0.0005

Data Index: 1025068 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0266. Min Act: -0.0005

Data Index: 107185 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0271. Min Act: -0.0005

Data Index: 1080229 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0265. Min Act: -0.0005

Data Index: 1596028 (Python Code)

Max Activating Token Index: 246

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0271. Min Act: -0.0005

Data Index: 1521981 (Python Code)

Max Activating Token Index: 199

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0270. Min Act: -0.0005

Data Index: 469071 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0264. Min Act: -0.0006

Data Index: 575081 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0263. Min Act: -0.0005

Data Index: 725608 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0263. Min Act: -0.0005

Data Index: 300731 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0267. Min Act: -0.0005

Data Index: 778433 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0262. Min Act: -0.0005

Data Index: 1084479 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0266. Min Act: -0.0005

Data Index: 816654 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0260. Min Act: -0.0005

Data Index: 1442714 (Python Code)

Max Activating Token Index: 661

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0266. Min Act: -0.0005

Data Index: 999434 (C4 (Web Text))

Max Activating Token Index: 253