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

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

Neuron 5092 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3299. Min Act: -0.0001

Data Index: 1352627 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3436. Min Act: -0.0001

Data Index: 1099293 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2984. Min Act: -0.0000

Data Index: 904751 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2908. Min Act: -0.0000

Data Index: 121992 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2778. Min Act: -0.0001

Data Index: 210785 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2668. Min Act: -0.0001

Data Index: 708475 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1191506 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2701. Min Act: -0.0001

Data Index: 1637987 (Python Code)

Max Activating Token Index: 321

Text #8

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1344789 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2502. Min Act: -0.0000

Data Index: 981593 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2492. Min Act: -0.0000

Data Index: 664949 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1499378 (Python Code)

Max Activating Token Index: 681

Text #12

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1504273 (Python Code)

Max Activating Token Index: 184

Text #13

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2454. Min Act: -0.0001

Data Index: 681464 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2318. Min Act: -0.0001

Data Index: 578052 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1519548 (Python Code)

Max Activating Token Index: 591

Text #16

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1139507 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2425. Min Act: -0.0001

Data Index: 444157 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1384250 (Python Code)

Max Activating Token Index: 301

Text #19

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1423110 (Python Code)

Max Activating Token Index: 122