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

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

Neuron 3382 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0000

Data Index: 364474 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1545. Min Act: -0.0000

Data Index: 674182 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1486. Min Act: -0.0000

Data Index: 908149 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1254377 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0000

Data Index: 955946 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1326030 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1449. Min Act: -0.0000

Data Index: 238306 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1532. Min Act: -0.0000

Data Index: 713795 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1638521 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1446. Min Act: -0.0000

Data Index: 81959 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1237123 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1141052 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1031974 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1637205 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1420. Min Act: -0.0000

Data Index: 212459 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1430061 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1337664 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1327463 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1343. Min Act: -0.0000

Data Index: 148369 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1287. Min Act: -0.0000

Data Index: 511001 (C4 (Web Text))

Max Activating Token Index: 488