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

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

Neuron 3602 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.5510. Min Act: -0.0001

Data Index: 1445151 (Python Code)

Max Activating Token Index: 596

Text #1

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.4944. Min Act: -0.0001

Data Index: 1656531 (Python Code)

Max Activating Token Index: 539

Text #2

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.5002. Min Act: -0.0001

Data Index: 1520547 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3570. Min Act: -0.0001

Data Index: 1546052 (Python Code)

Max Activating Token Index: 533

Text #4

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.4328. Min Act: -0.0001

Data Index: 1541186 (Python Code)

Max Activating Token Index: 627

Text #5

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2246. Min Act: -0.0001

Data Index: 1405817 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1126. Min Act: -0.0001

Data Index: 1369392 (Python Code)

Max Activating Token Index: 445

Text #7

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1538. Min Act: -0.0001

Data Index: 1479580 (Python Code)

Max Activating Token Index: 173

Text #8

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3149. Min Act: -0.0001

Data Index: 1485287 (Python Code)

Max Activating Token Index: 261

Text #9

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2382. Min Act: -0.0001

Data Index: 1489454 (Python Code)

Max Activating Token Index: 866

Text #10

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9421. Min Act: -0.0001

Data Index: 1454791 (Python Code)

Max Activating Token Index: 318

Text #11

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9707. Min Act: -0.0001

Data Index: 1363649 (Python Code)

Max Activating Token Index: 398

Text #12

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9815. Min Act: -0.0001

Data Index: 1366546 (Python Code)

Max Activating Token Index: 870

Text #13

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1040. Min Act: -0.0001

Data Index: 1363439 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0561. Min Act: -0.0001

Data Index: 1636866 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2848. Min Act: -0.0001

Data Index: 1453479 (Python Code)

Max Activating Token Index: 410

Text #16

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1948. Min Act: -0.0001

Data Index: 1384807 (Python Code)

Max Activating Token Index: 509

Text #17

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1319. Min Act: -0.0001

Data Index: 1416331 (Python Code)

Max Activating Token Index: 965

Text #18

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0450. Min Act: -0.0001

Data Index: 1437329 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9172. Min Act: -0.0001

Data Index: 1401478 (Python Code)

Max Activating Token Index: 438