Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1693 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1530. Min Act: -0.0002

Data Index: 1534382 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1486. Min Act: -0.0002

Data Index: 1488869 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1440. Min Act: -0.0002

Data Index: 1597868 (Python Code)

Max Activating Token Index: 184

Text #3

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1424. Min Act: -0.0002

Data Index: 1546476 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1380. Min Act: -0.0002

Data Index: 160765 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1397. Min Act: -0.0002

Data Index: 1498935 (Python Code)

Max Activating Token Index: 758

Text #6

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1402. Min Act: -0.0002

Data Index: 1362947 (Python Code)

Max Activating Token Index: 57

Text #7

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1590234 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1346. Min Act: -0.0002

Data Index: 1584607 (Python Code)

Max Activating Token Index: 371

Text #9

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1355. Min Act: -0.0002

Data Index: 1606244 (Python Code)

Max Activating Token Index: 698

Text #10

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1358. Min Act: -0.0002

Data Index: 773969 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1322. Min Act: -0.0002

Data Index: 261467 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1327. Min Act: -0.0002

Data Index: 72082 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1314. Min Act: -0.0002

Data Index: 1639254 (Python Code)

Max Activating Token Index: 482

Text #14

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1375. Min Act: -0.0002

Data Index: 952255 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1369. Min Act: -0.0001

Data Index: 229811 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1292. Min Act: -0.0002

Data Index: 1520590 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1357. Min Act: -0.0002

Data Index: 1652301 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1281. Min Act: -0.0002

Data Index: 1428139 (Python Code)

Max Activating Token Index: 814

Text #19

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1165. Min Act: -0.0002

Data Index: 1520707 (Python Code)

Max Activating Token Index: 684