Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4068 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.2036. Min Act: -0.0000

Data Index: 1331222 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1346414 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1596. Min Act: -0.0000

Data Index: 273880 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1651. Min Act: -0.0001

Data Index: 479797 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1709. Min Act: -0.0000

Data Index: 92265 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1632. Min Act: -0.0000

Data Index: 277711 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1234514 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1076964 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1582. Min Act: -0.0000

Data Index: 934504 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1532. Min Act: -0.0000

Data Index: 125576 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1430. Min Act: -0.0000

Data Index: 209997 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1454. Min Act: -0.0001

Data Index: 458826 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1395. Min Act: -0.0000

Data Index: 773018 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1109672 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1288. Min Act: -0.0000

Data Index: 682391 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1301. Min Act: -0.0000

Data Index: 73048 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1333. Min Act: -0.0000

Data Index: 123647 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1192. Min Act: -0.0000

Data Index: 137304 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1379. Min Act: -0.0000

Data Index: 705641 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1275. Min Act: -0.0000

Data Index: 974621 (C4 (Web Text))

Max Activating Token Index: 998