Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2255 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1674. Min Act: -0.0001

Data Index: 1586295 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1619124 (Python Code)

Max Activating Token Index: 91

Text #2

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1369477 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1434673 (Python Code)

Max Activating Token Index: 401

Text #4

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1652507 (Python Code)

Max Activating Token Index: 412

Text #5

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1441164 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1371115 (Python Code)

Max Activating Token Index: 308

Text #7

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1432191 (Python Code)

Max Activating Token Index: 100

Text #8

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1519258 (Python Code)

Max Activating Token Index: 104

Text #9

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1643522 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1647159 (Python Code)

Max Activating Token Index: 545

Text #11

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1515383 (Python Code)

Max Activating Token Index: 358

Text #12

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1601018 (Python Code)

Max Activating Token Index: 485

Text #13

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1408422 (Python Code)

Max Activating Token Index: 860

Text #14

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1635436 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1631996 (Python Code)

Max Activating Token Index: 392

Text #16

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1465517 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1280. Min Act: -0.0001

Data Index: 1576707 (Python Code)

Max Activating Token Index: 560

Text #18

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1640001 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1251. Min Act: -0.0001

Data Index: 1412349 (Python Code)

Max Activating Token Index: 23