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

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

Neuron 3043 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.7614. Min Act: -0.0001

Data Index: 1475355 (Python Code)

Max Activating Token Index: 194

Text #1

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.7385. Min Act: -0.0001

Data Index: 1483332 (Python Code)

Max Activating Token Index: 52

Text #2

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.7168. Min Act: -0.0001

Data Index: 1575877 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6927. Min Act: -0.0001

Data Index: 1421453 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6799. Min Act: -0.0001

Data Index: 1370454 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6799. Min Act: -0.0001

Data Index: 1422468 (Python Code)

Max Activating Token Index: 152

Text #6

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1545068 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6763. Min Act: -0.0001

Data Index: 1395318 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6582. Min Act: -0.0001

Data Index: 1541433 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1629731 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6407. Min Act: -0.0001

Data Index: 1550698 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6391. Min Act: -0.0001

Data Index: 1498283 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6311. Min Act: -0.0001

Data Index: 1394046 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6276. Min Act: -0.0001

Data Index: 1467028 (Python Code)

Max Activating Token Index: 203

Text #14

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6218. Min Act: -0.0001

Data Index: 1412104 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6412. Min Act: -0.0001

Data Index: 1404790 (Python Code)

Max Activating Token Index: 663

Text #16

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6203. Min Act: -0.0001

Data Index: 1378067 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6150. Min Act: -0.0001

Data Index: 1375860 (Python Code)

Max Activating Token Index: 515

Text #18

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6224. Min Act: -0.0001

Data Index: 1420167 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 0.7614. Min Range: -0.7614

Max Act: 0.6067. Min Act: -0.0002

Data Index: 1496217 (Python Code)

Max Activating Token Index: 434