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

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

Neuron 4668 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: 0.1635. Min Range: -0.1635

Max Act: 0.1635. Min Act: -0.0002

Data Index: 1267315 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1635. Min Act: -0.0002

Data Index: 1635375 (Python Code)

Max Activating Token Index: 492

Text #2

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1621. Min Act: -0.0002

Data Index: 1654201 (Python Code)

Max Activating Token Index: 930

Text #3

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1530. Min Act: -0.0002

Data Index: 1620015 (Python Code)

Max Activating Token Index: 922

Text #4

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1551054 (Python Code)

Max Activating Token Index: 362

Text #5

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1459. Min Act: -0.0002

Data Index: 1510245 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1631877 (Python Code)

Max Activating Token Index: 243

Text #7

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1422. Min Act: -0.0002

Data Index: 1558283 (Python Code)

Max Activating Token Index: 189

Text #8

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1421. Min Act: -0.0002

Data Index: 1582250 (Python Code)

Max Activating Token Index: 362

Text #9

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1434. Min Act: -0.0002

Data Index: 1539959 (Python Code)

Max Activating Token Index: 633

Text #10

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1402. Min Act: -0.0002

Data Index: 1541224 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1369. Min Act: -0.0002

Data Index: 1493403 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1374. Min Act: -0.0002

Data Index: 1189784 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1372. Min Act: -0.0002

Data Index: 1471774 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1370. Min Act: -0.0002

Data Index: 1536520 (Python Code)

Max Activating Token Index: 898

Text #15

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1569961 (Python Code)

Max Activating Token Index: 654

Text #16

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1406325 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1344. Min Act: -0.0002

Data Index: 1531770 (Python Code)

Max Activating Token Index: 496

Text #18

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1645155 (Python Code)

Max Activating Token Index: 846

Text #19

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1330. Min Act: -0.0002

Data Index: 1509156 (Python Code)

Max Activating Token Index: 650