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

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

Neuron 579 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4336. Min Range: -4.4336

Max Act: 4.4336. Min Act: -0.0000

Data Index: 1487432 (Python Code)

Max Activating Token Index: 1015

Text #1

Max Range: 4.4336. Min Range: -4.4336

Max Act: 4.1670. Min Act: -0.0000

Data Index: 1620186 (Python Code)

Max Activating Token Index: 955

Text #2

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.9415. Min Act: -0.0000

Data Index: 1460952 (Python Code)

Max Activating Token Index: 473

Text #3

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.7918. Min Act: -0.0000

Data Index: 1408722 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.8523. Min Act: -0.0000

Data Index: 1471135 (Python Code)

Max Activating Token Index: 539

Text #5

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.7504. Min Act: -0.0000

Data Index: 1545406 (Python Code)

Max Activating Token Index: 664

Text #6

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.6420. Min Act: -0.0000

Data Index: 1595616 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.1647. Min Act: -0.0000

Data Index: 1433051 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.2282. Min Act: -0.0000

Data Index: 1432055 (Python Code)

Max Activating Token Index: 994

Text #9

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.4938. Min Act: -0.0000

Data Index: 1546599 (Python Code)

Max Activating Token Index: 989

Text #10

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.5027. Min Act: -0.0000

Data Index: 1500479 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.4407. Min Act: -0.0000

Data Index: 1631561 (Python Code)

Max Activating Token Index: 84

Text #12

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.4136. Min Act: -0.0000

Data Index: 1564736 (Python Code)

Max Activating Token Index: 997

Text #13

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.3883. Min Act: -0.0000

Data Index: 1605848 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.1037. Min Act: -0.0000

Data Index: 1409088 (Python Code)

Max Activating Token Index: 785

Text #15

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.1988. Min Act: -0.0000

Data Index: 1586697 (Python Code)

Max Activating Token Index: 233

Text #16

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.0050. Min Act: -0.0000

Data Index: 1529593 (Python Code)

Max Activating Token Index: 844

Text #17

Max Range: 4.4336. Min Range: -4.4336

Max Act: 2.9180. Min Act: -0.0000

Data Index: 1546157 (Python Code)

Max Activating Token Index: 657

Text #18

Max Range: 4.4336. Min Range: -4.4336

Max Act: 3.1656. Min Act: -0.0000

Data Index: 1410120 (Python Code)

Max Activating Token Index: 652

Text #19

Max Range: 4.4336. Min Range: -4.4336

Max Act: 2.8687. Min Act: -0.0000

Data Index: 1493755 (Python Code)

Max Activating Token Index: 679