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

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

Neuron 2872 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.8764. Min Act: -0.0000

Data Index: 1559248 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5655. Min Act: -0.0001

Data Index: 1632921 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.6364. Min Act: -0.0000

Data Index: 1476502 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.6213. Min Act: -0.0000

Data Index: 1440958 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.6010. Min Act: -0.0000

Data Index: 1514981 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.6429. Min Act: -0.0001

Data Index: 1440888 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1474478 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5126. Min Act: -0.0001

Data Index: 1585036 (Python Code)

Max Activating Token Index: 656

Text #8

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4587. Min Act: -0.0000

Data Index: 1366841 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5974. Min Act: -0.0000

Data Index: 1399976 (Python Code)

Max Activating Token Index: 484

Text #10

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4537. Min Act: -0.0000

Data Index: 1587614 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4866. Min Act: -0.0000

Data Index: 1524394 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.6527. Min Act: -0.0000

Data Index: 1381355 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5000. Min Act: -0.0000

Data Index: 1502187 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5467. Min Act: -0.0000

Data Index: 1528615 (Python Code)

Max Activating Token Index: 702

Text #15

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4422. Min Act: -0.0000

Data Index: 1495917 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4888. Min Act: -0.0000

Data Index: 1613301 (Python Code)

Max Activating Token Index: 264

Text #17

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1401429 (Python Code)

Max Activating Token Index: 46

Text #18

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.3867. Min Act: -0.0001

Data Index: 1529716 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1443820 (Python Code)

Max Activating Token Index: 669