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

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

Neuron 5232 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: 0.1524. Min Range: -0.1524

Max Act: 0.1524. Min Act: -0.0002

Data Index: 1435731 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1501. Min Act: -0.0002

Data Index: 1419856 (Python Code)

Max Activating Token Index: 230

Text #2

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1482. Min Act: -0.0002

Data Index: 1526263 (Python Code)

Max Activating Token Index: 78

Text #3

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1443. Min Act: -0.0002

Data Index: 1512217 (Python Code)

Max Activating Token Index: 258

Text #4

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1407. Min Act: -0.0002

Data Index: 1552725 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1377. Min Act: -0.0002

Data Index: 1465178 (Python Code)

Max Activating Token Index: 417

Text #6

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1395. Min Act: -0.0002

Data Index: 1548740 (Python Code)

Max Activating Token Index: 972

Text #7

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1395. Min Act: -0.0002

Data Index: 1392079 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1408. Min Act: -0.0002

Data Index: 1466650 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1363. Min Act: -0.0002

Data Index: 1523816 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1382. Min Act: -0.0002

Data Index: 1471403 (Python Code)

Max Activating Token Index: 257

Text #11

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1348. Min Act: -0.0002

Data Index: 1425746 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1330. Min Act: -0.0002

Data Index: 1473864 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1359. Min Act: -0.0002

Data Index: 1442247 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1307. Min Act: -0.0002

Data Index: 1478635 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1584825 (Python Code)

Max Activating Token Index: 51

Text #16

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1319. Min Act: -0.0002

Data Index: 676939 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1314. Min Act: -0.0002

Data Index: 1453568 (Python Code)

Max Activating Token Index: 42

Text #18

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1391634 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1293. Min Act: -0.0002

Data Index: 1362434 (Python Code)

Max Activating Token Index: 73