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

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

Neuron 309 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: 0.1631. Min Range: -0.1631

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1369724 (Python Code)

Max Activating Token Index: 523

Text #1

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1384464 (Python Code)

Max Activating Token Index: 551

Text #2

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1487938 (Python Code)

Max Activating Token Index: 507

Text #3

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1409563 (Python Code)

Max Activating Token Index: 476

Text #4

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1431992 (Python Code)

Max Activating Token Index: 531

Text #5

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1351. Min Act: -0.0001

Data Index: 1627851 (Python Code)

Max Activating Token Index: 904

Text #6

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1390542 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1569807 (Python Code)

Max Activating Token Index: 1002

Text #8

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1484322 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1466370 (Python Code)

Max Activating Token Index: 873

Text #10

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1410941 (Python Code)

Max Activating Token Index: 926

Text #11

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1589629 (Python Code)

Max Activating Token Index: 324

Text #12

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1615116 (Python Code)

Max Activating Token Index: 965

Text #13

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1567969 (Python Code)

Max Activating Token Index: 982

Text #14

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1428616 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1366055 (Python Code)

Max Activating Token Index: 960

Text #16

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1485292 (Python Code)

Max Activating Token Index: 763

Text #17

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1321. Min Act: -0.0001

Data Index: 1505711 (Python Code)

Max Activating Token Index: 1008

Text #18

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1477155 (Python Code)

Max Activating Token Index: 589

Text #19

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1390915 (Python Code)

Max Activating Token Index: 440