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

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

Neuron 1507 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0005

Data Index: 257624 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0298. Min Act: -0.0005

Data Index: 914469 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0290. Min Act: -0.0005

Data Index: 680047 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0274. Min Act: -0.0005

Data Index: 210709 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0266. Min Act: -0.0005

Data Index: 1558167 (Python Code)

Max Activating Token Index: 656

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0264. Min Act: -0.0005

Data Index: 668141 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0261. Min Act: -0.0005

Data Index: 1624993 (Python Code)

Max Activating Token Index: 405

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0277. Min Act: -0.0005

Data Index: 1562442 (Python Code)

Max Activating Token Index: 651

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1384701 (Python Code)

Max Activating Token Index: 613

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0261. Min Act: -0.0005

Data Index: 1391537 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0248. Min Act: -0.0005

Data Index: 1383674 (Python Code)

Max Activating Token Index: 399

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1480314 (Python Code)

Max Activating Token Index: 847

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0261. Min Act: -0.0005

Data Index: 1611007 (Python Code)

Max Activating Token Index: 619

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0261. Min Act: -0.0005

Data Index: 309293 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0269. Min Act: -0.0005

Data Index: 1508246 (Python Code)

Max Activating Token Index: 297

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0234. Min Act: -0.0005

Data Index: 1379837 (Python Code)

Max Activating Token Index: 985

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1454137 (Python Code)

Max Activating Token Index: 882

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0252. Min Act: -0.0005

Data Index: 1466569 (Python Code)

Max Activating Token Index: 402

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0265. Min Act: -0.0005

Data Index: 1170162 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0260. Min Act: -0.0005

Data Index: 552132 (C4 (Web Text))

Max Activating Token Index: 297