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

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

Neuron 2867 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1401133 (Python Code)

Max Activating Token Index: 637

Text #1

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1393275 (Python Code)

Max Activating Token Index: 822

Text #2

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1372. Min Act: -0.0001

Data Index: 1360859 (Python Code)

Max Activating Token Index: 259

Text #3

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1501032 (Python Code)

Max Activating Token Index: 375

Text #4

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1387321 (Python Code)

Max Activating Token Index: 646

Text #5

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1626510 (Python Code)

Max Activating Token Index: 565

Text #6

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1619112 (Python Code)

Max Activating Token Index: 188

Text #7

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1533465 (Python Code)

Max Activating Token Index: 304

Text #8

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1455239 (Python Code)

Max Activating Token Index: 966

Text #9

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1602118 (Python Code)

Max Activating Token Index: 444

Text #10

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1436160 (Python Code)

Max Activating Token Index: 802

Text #11

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1547124 (Python Code)

Max Activating Token Index: 546

Text #12

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1396553 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1436240 (Python Code)

Max Activating Token Index: 406

Text #14

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1543801 (Python Code)

Max Activating Token Index: 458

Text #15

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1496119 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1514813 (Python Code)

Max Activating Token Index: 767

Text #17

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1578363 (Python Code)

Max Activating Token Index: 564

Text #18

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1511684 (Python Code)

Max Activating Token Index: 474

Text #19

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1378658 (Python Code)

Max Activating Token Index: 407