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

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

Neuron 1753 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0077. Min Range: -5.0077

Max Act: 5.0077. Min Act: -0.0001

Data Index: 1419262 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.0623. Min Act: -0.0001

Data Index: 1564129 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 5.0077. Min Range: -5.0077

Max Act: 3.5521. Min Act: -0.0001

Data Index: 1510620 (Python Code)

Max Activating Token Index: 17

Text #3

Max Range: 5.0077. Min Range: -5.0077

Max Act: 3.2199. Min Act: -0.0001

Data Index: 1618003 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 5.0077. Min Range: -5.0077

Max Act: 3.1741. Min Act: -0.0001

Data Index: 1507545 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 5.0077. Min Range: -5.0077

Max Act: 3.0107. Min Act: -0.0001

Data Index: 1529119 (Python Code)

Max Activating Token Index: 559

Text #6

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.9919. Min Act: -0.0001

Data Index: 1418489 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.9273. Min Act: -0.0001

Data Index: 1366475 (Python Code)

Max Activating Token Index: 49

Text #8

Max Range: 5.0077. Min Range: -5.0077

Max Act: 3.0474. Min Act: -0.0001

Data Index: 1630409 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 5.0077. Min Range: -5.0077

Max Act: 3.0701. Min Act: -0.0001

Data Index: 1521179 (Python Code)

Max Activating Token Index: 668

Text #10

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.6204. Min Act: -0.0001

Data Index: 1375223 (Python Code)

Max Activating Token Index: 871

Text #11

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.4302. Min Act: -0.0001

Data Index: 1590775 (Python Code)

Max Activating Token Index: 297

Text #12

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.8261. Min Act: -0.0001

Data Index: 1541371 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.7344. Min Act: -0.0001

Data Index: 1401282 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.7763. Min Act: -0.0001

Data Index: 1555313 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.9058. Min Act: -0.0001

Data Index: 1477589 (Python Code)

Max Activating Token Index: 696

Text #16

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.7357. Min Act: -0.0001

Data Index: 1605705 (Python Code)

Max Activating Token Index: 898

Text #17

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.5888. Min Act: -0.0001

Data Index: 1584835 (Python Code)

Max Activating Token Index: 398

Text #18

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.4162. Min Act: -0.0001

Data Index: 1595210 (Python Code)

Max Activating Token Index: 146

Text #19

Max Range: 5.0077. Min Range: -5.0077

Max Act: 2.6920. Min Act: -0.0001

Data Index: 1539511 (Python Code)

Max Activating Token Index: 434