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

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

Neuron 2478 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1202632 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.5980. Min Act: -0.0000

Data Index: 586056 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.5061. Min Act: -0.0000

Data Index: 383810 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.3797. Min Act: -0.0000

Data Index: 1374239 (Python Code)

Max Activating Token Index: 335

Text #4

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.2863. Min Act: -0.0000

Data Index: 906941 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.1884. Min Act: -0.0000

Data Index: 717946 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1478692 (Python Code)

Max Activating Token Index: 681

Text #7

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1448723 (Python Code)

Max Activating Token Index: 763

Text #8

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9457. Min Act: -0.0000

Data Index: 869051 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9884. Min Act: -0.0000

Data Index: 371324 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9566. Min Act: -0.0000

Data Index: 641054 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1391708 (Python Code)

Max Activating Token Index: 449

Text #12

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1251944 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9528. Min Act: -0.0000

Data Index: 513794 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1453816 (Python Code)

Max Activating Token Index: 521

Text #15

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.0402. Min Act: -0.0000

Data Index: 181520 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1218461 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.8565. Min Act: -0.0000

Data Index: 250250 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1654823 (Python Code)

Max Activating Token Index: 940

Text #19

Max Range: 1.6044. Min Range: -1.6044

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1540165 (Python Code)

Max Activating Token Index: 394