Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3494 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1249919 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1644. Min Act: -0.0000

Data Index: 54776 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1185465 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1344927 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1604448 (Python Code)

Max Activating Token Index: 211

Text #5

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1636577 (Python Code)

Max Activating Token Index: 250

Text #6

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1400. Min Act: -0.0000

Data Index: 1370336 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1515356 (Python Code)

Max Activating Token Index: 923

Text #8

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1398826 (Python Code)

Max Activating Token Index: 181

Text #9

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1602289 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1519460 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1491300 (Python Code)

Max Activating Token Index: 146

Text #12

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1412976 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1586830 (Python Code)

Max Activating Token Index: 1005

Text #14

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1496463 (Python Code)

Max Activating Token Index: 510

Text #15

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1414636 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1604167 (Python Code)

Max Activating Token Index: 68

Text #17

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1525411 (Python Code)

Max Activating Token Index: 269

Text #18

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1529582 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1438000 (Python Code)

Max Activating Token Index: 91