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

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

Neuron 1846 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: 0.3307. Min Range: -0.3307

Max Act: 0.3307. Min Act: -0.0001

Data Index: 1458001 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2659. Min Act: -0.0001

Data Index: 1623161 (Python Code)

Max Activating Token Index: 889

Text #2

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2362. Min Act: -0.0001

Data Index: 1385031 (Python Code)

Max Activating Token Index: 433

Text #3

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2408. Min Act: -0.0001

Data Index: 1552375 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2672. Min Act: -0.0001

Data Index: 1479257 (Python Code)

Max Activating Token Index: 693

Text #5

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1527106 (Python Code)

Max Activating Token Index: 690

Text #6

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2324. Min Act: -0.0001

Data Index: 1472634 (Python Code)

Max Activating Token Index: 523

Text #7

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1494384 (Python Code)

Max Activating Token Index: 715

Text #8

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2185. Min Act: -0.0001

Data Index: 1549235 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2169. Min Act: -0.0001

Data Index: 1398930 (Python Code)

Max Activating Token Index: 542

Text #10

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1926. Min Act: -0.0001

Data Index: 1541055 (Python Code)

Max Activating Token Index: 308

Text #11

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1573463 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1513143 (Python Code)

Max Activating Token Index: 366

Text #13

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1824. Min Act: -0.0001

Data Index: 1463450 (Python Code)

Max Activating Token Index: 108

Text #14

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1455710 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2133. Min Act: -0.0001

Data Index: 1547624 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1643999 (Python Code)

Max Activating Token Index: 62

Text #17

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1495063 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1298922 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1861. Min Act: -0.0001

Data Index: 1645033 (Python Code)

Max Activating Token Index: 364