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

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

Neuron 892 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1604. Min Act: -0.0003

Data Index: 1594937 (Python Code)

Max Activating Token Index: 420

Text #1

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1487. Min Act: -0.0003

Data Index: 1504416 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1395. Min Act: -0.0003

Data Index: 1371193 (Python Code)

Max Activating Token Index: 266

Text #3

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1358. Min Act: -0.0003

Data Index: 1564984 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1319. Min Act: -0.0003

Data Index: 1380589 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1315. Min Act: -0.0003

Data Index: 1540676 (Python Code)

Max Activating Token Index: 134

Text #6

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1325. Min Act: -0.0003

Data Index: 1623170 (Python Code)

Max Activating Token Index: 990

Text #7

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1218. Min Act: -0.0003

Data Index: 1580295 (Python Code)

Max Activating Token Index: 132

Text #8

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1410. Min Act: -0.0003

Data Index: 1648666 (Python Code)

Max Activating Token Index: 895

Text #9

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1254. Min Act: -0.0003

Data Index: 1488445 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1355. Min Act: -0.0003

Data Index: 1376962 (Python Code)

Max Activating Token Index: 198

Text #11

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1306. Min Act: -0.0003

Data Index: 1492879 (Python Code)

Max Activating Token Index: 410

Text #12

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1314. Min Act: -0.0003

Data Index: 1364237 (Python Code)

Max Activating Token Index: 85

Text #13

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1310. Min Act: -0.0003

Data Index: 1438548 (Python Code)

Max Activating Token Index: 388

Text #14

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1249. Min Act: -0.0003

Data Index: 1495198 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1052. Min Act: -0.0003

Data Index: 1384960 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1235. Min Act: -0.0003

Data Index: 1367716 (Python Code)

Max Activating Token Index: 355

Text #17

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1233. Min Act: -0.0003

Data Index: 1599820 (Python Code)

Max Activating Token Index: 373

Text #18

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1273. Min Act: -0.0003

Data Index: 1431112 (Python Code)

Max Activating Token Index: 502

Text #19

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1278. Min Act: -0.0003

Data Index: 1419655 (Python Code)

Max Activating Token Index: 99