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

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

Neuron 2618 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: 0.1906. Min Range: -0.1906

Max Act: 0.1906. Min Act: -0.0002

Data Index: 1455737 (Python Code)

Max Activating Token Index: 244

Text #1

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1571. Min Act: -0.0002

Data Index: 1440361 (Python Code)

Max Activating Token Index: 122

Text #2

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1524. Min Act: -0.0002

Data Index: 1372972 (Python Code)

Max Activating Token Index: 250

Text #3

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1469. Min Act: -0.0002

Data Index: 1385467 (Python Code)

Max Activating Token Index: 258

Text #4

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1485. Min Act: -0.0002

Data Index: 1511811 (Python Code)

Max Activating Token Index: 706

Text #5

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1461. Min Act: -0.0002

Data Index: 1619570 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1402. Min Act: -0.0002

Data Index: 1369535 (Python Code)

Max Activating Token Index: 241

Text #7

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1412. Min Act: -0.0002

Data Index: 1571559 (Python Code)

Max Activating Token Index: 111

Text #8

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1442. Min Act: -0.0002

Data Index: 1586084 (Python Code)

Max Activating Token Index: 126

Text #9

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1651096 (Python Code)

Max Activating Token Index: 151

Text #10

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1435. Min Act: -0.0002

Data Index: 1515096 (Python Code)

Max Activating Token Index: 966

Text #11

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1381. Min Act: -0.0002

Data Index: 1515272 (Python Code)

Max Activating Token Index: 457

Text #12

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1402. Min Act: -0.0002

Data Index: 1562529 (Python Code)

Max Activating Token Index: 407

Text #13

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1377. Min Act: -0.0002

Data Index: 1597931 (Python Code)

Max Activating Token Index: 524

Text #14

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1382. Min Act: -0.0002

Data Index: 1625890 (Python Code)

Max Activating Token Index: 390

Text #15

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1343. Min Act: -0.0002

Data Index: 1407345 (Python Code)

Max Activating Token Index: 898

Text #16

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1321. Min Act: -0.0002

Data Index: 1386496 (Python Code)

Max Activating Token Index: 676

Text #17

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1566949 (Python Code)

Max Activating Token Index: 857

Text #18

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1290. Min Act: -0.0002

Data Index: 1479313 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1279. Min Act: -0.0002

Data Index: 1412616 (Python Code)

Max Activating Token Index: 875