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

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

Neuron 608 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: 0.1563. Min Range: -0.1563

Max Act: 0.1563. Min Act: -0.0002

Data Index: 1537430 (Python Code)

Max Activating Token Index: 323

Text #1

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1491. Min Act: -0.0002

Data Index: 1517177 (Python Code)

Max Activating Token Index: 293

Text #2

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1394. Min Act: -0.0002

Data Index: 1434424 (Python Code)

Max Activating Token Index: 220

Text #3

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1384. Min Act: -0.0002

Data Index: 1621957 (Python Code)

Max Activating Token Index: 431

Text #4

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1365. Min Act: -0.0002

Data Index: 1609700 (Python Code)

Max Activating Token Index: 452

Text #5

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1382667 (Python Code)

Max Activating Token Index: 450

Text #6

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1646785 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1340. Min Act: -0.0002

Data Index: 1645317 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1431205 (Python Code)

Max Activating Token Index: 290

Text #9

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1344. Min Act: -0.0002

Data Index: 1533943 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1478216 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1621930 (Python Code)

Max Activating Token Index: 229

Text #12

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1610085 (Python Code)

Max Activating Token Index: 143

Text #13

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1319. Min Act: -0.0002

Data Index: 1589215 (Python Code)

Max Activating Token Index: 427

Text #14

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1299. Min Act: -0.0002

Data Index: 1390820 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1297. Min Act: -0.0002

Data Index: 1534482 (Python Code)

Max Activating Token Index: 153

Text #16

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1645856 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1571155 (Python Code)

Max Activating Token Index: 105

Text #18

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1293. Min Act: -0.0002

Data Index: 1578640 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1436002 (Python Code)

Max Activating Token Index: 415