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

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

Neuron 3125 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: 0.2033. Min Range: -0.2033

Max Act: 0.2033. Min Act: -0.0002

Data Index: 1619521 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1665. Min Act: -0.0002

Data Index: 1506312 (Python Code)

Max Activating Token Index: 464

Text #2

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1624. Min Act: -0.0002

Data Index: 1563078 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1549. Min Act: -0.0002

Data Index: 1378162 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1523. Min Act: -0.0002

Data Index: 1400998 (Python Code)

Max Activating Token Index: 267

Text #5

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1379. Min Act: -0.0002

Data Index: 1477868 (Python Code)

Max Activating Token Index: 48

Text #6

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1368. Min Act: -0.0002

Data Index: 1475459 (Python Code)

Max Activating Token Index: 450

Text #7

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1378. Min Act: -0.0002

Data Index: 1495002 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1340. Min Act: -0.0002

Data Index: 35943 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1325. Min Act: -0.0002

Data Index: 1544535 (Python Code)

Max Activating Token Index: 263

Text #10

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1310. Min Act: -0.0002

Data Index: 1596604 (Python Code)

Max Activating Token Index: 327

Text #11

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1311. Min Act: -0.0002

Data Index: 1524360 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1261. Min Act: -0.0002

Data Index: 1622605 (Python Code)

Max Activating Token Index: 213

Text #13

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1287. Min Act: -0.0002

Data Index: 841567 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1275405 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1547894 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1268. Min Act: -0.0002

Data Index: 1566128 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1624774 (Python Code)

Max Activating Token Index: 581

Text #18

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1587974 (Python Code)

Max Activating Token Index: 867

Text #19

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1207. Min Act: -0.0002

Data Index: 1654100 (Python Code)

Max Activating Token Index: 406