Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2547. Min Act: -0.0001

Data Index: 249732 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1957. Min Act: -0.0001

Data Index: 925557 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1614. Min Act: -0.0000

Data Index: 261998 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1697. Min Act: -0.0001

Data Index: 890358 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1587. Min Act: -0.0001

Data Index: 429262 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1433. Min Act: -0.0000

Data Index: 545991 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1560. Min Act: -0.0000

Data Index: 507581 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1504. Min Act: -0.0001

Data Index: 754181 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1535. Min Act: -0.0000

Data Index: 572363 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1534. Min Act: -0.0001

Data Index: 535211 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1411. Min Act: -0.0000

Data Index: 199515 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1397. Min Act: -0.0000

Data Index: 986119 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1439. Min Act: -0.0001

Data Index: 277835 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1257434 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1254. Min Act: -0.0001

Data Index: 160360 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1274. Min Act: -0.0000

Data Index: 656385 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1216. Min Act: -0.0000

Data Index: 474364 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1338. Min Act: -0.0001

Data Index: 333149 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1333243 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1327. Min Act: -0.0000

Data Index: 986001 (C4 (Web Text))

Max Activating Token Index: 404