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

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

Neuron 5059 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0002

Data Index: 1507702 (Python Code)

Max Activating Token Index: 252

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1509. Min Act: -0.0002

Data Index: 1407094 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1522. Min Act: -0.0002

Data Index: 705060 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1478. Min Act: -0.0002

Data Index: 1418207 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1458. Min Act: -0.0002

Data Index: 1520687 (Python Code)

Max Activating Token Index: 127

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1381. Min Act: -0.0002

Data Index: 1508997 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1466695 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1395. Min Act: -0.0002

Data Index: 1395176 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1258810 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1361. Min Act: -0.0002

Data Index: 1602830 (Python Code)

Max Activating Token Index: 582

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1344. Min Act: -0.0002

Data Index: 1645254 (Python Code)

Max Activating Token Index: 58

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1363. Min Act: -0.0002

Data Index: 1495511 (Python Code)

Max Activating Token Index: 667

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1360475 (Python Code)

Max Activating Token Index: 220

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1298. Min Act: -0.0002

Data Index: 1443583 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1285. Min Act: -0.0002

Data Index: 1429298 (Python Code)

Max Activating Token Index: 832

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1294. Min Act: -0.0002

Data Index: 734195 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1286. Min Act: -0.0002

Data Index: 1606587 (Python Code)

Max Activating Token Index: 217

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1570301 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1462901 (Python Code)

Max Activating Token Index: 68

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1287. Min Act: -0.0002

Data Index: 1207234 (C4 (Web Text))

Max Activating Token Index: 280