Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1719 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1613662 (Python Code)

Max Activating Token Index: 883

Text #1

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1492. Min Act: -0.0001

Data Index: 1573181 (Python Code)

Max Activating Token Index: 277

Text #2

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1442778 (Python Code)

Max Activating Token Index: 914

Text #3

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1372980 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1392523 (Python Code)

Max Activating Token Index: 863

Text #5

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1552644 (Python Code)

Max Activating Token Index: 279

Text #6

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1507631 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1521279 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1594895 (Python Code)

Max Activating Token Index: 625

Text #9

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1581536 (Python Code)

Max Activating Token Index: 517

Text #10

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1388540 (Python Code)

Max Activating Token Index: 854

Text #11

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1379251 (Python Code)

Max Activating Token Index: 276

Text #12

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1543563 (Python Code)

Max Activating Token Index: 679

Text #13

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1504635 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1543954 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1373958 (Python Code)

Max Activating Token Index: 838

Text #16

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1565151 (Python Code)

Max Activating Token Index: 255

Text #17

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1615021 (Python Code)

Max Activating Token Index: 401

Text #18

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1527847 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1483348 (Python Code)

Max Activating Token Index: 706