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

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

Neuron 1644 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1550151 (Python Code)

Max Activating Token Index: 735

Text #1

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1425323 (Python Code)

Max Activating Token Index: 696

Text #2

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1434228 (Python Code)

Max Activating Token Index: 576

Text #3

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1482361 (Python Code)

Max Activating Token Index: 332

Text #4

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1485. Min Act: -0.0001

Data Index: 1630591 (Python Code)

Max Activating Token Index: 470

Text #5

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1579399 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1644356 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1533092 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1477001 (Python Code)

Max Activating Token Index: 574

Text #9

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1378498 (Python Code)

Max Activating Token Index: 731

Text #10

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1537691 (Python Code)

Max Activating Token Index: 858

Text #11

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1559059 (Python Code)

Max Activating Token Index: 804

Text #12

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1449270 (Python Code)

Max Activating Token Index: 599

Text #13

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1560829 (Python Code)

Max Activating Token Index: 233

Text #14

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1431036 (Python Code)

Max Activating Token Index: 931

Text #15

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1508163 (Python Code)

Max Activating Token Index: 251

Text #16

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1413293 (Python Code)

Max Activating Token Index: 661

Text #17

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1649007 (Python Code)

Max Activating Token Index: 954

Text #18

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1556095 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1383597 (Python Code)

Max Activating Token Index: 806