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

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

Neuron 1075 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0967. Min Range: -2.0967

Max Act: 2.0127. Min Act: -0.0000

Data Index: 1360078 (Python Code)

Max Activating Token Index: 415

Text #1

Max Range: 2.0967. Min Range: -2.0967

Max Act: 2.0967. Min Act: -0.0000

Data Index: 1410588 (Python Code)

Max Activating Token Index: 76

Text #2

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.9772. Min Act: -0.0000

Data Index: 1654082 (Python Code)

Max Activating Token Index: 965

Text #3

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.9395. Min Act: -0.0000

Data Index: 1489448 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.7318. Min Act: -0.0000

Data Index: 584786 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.8179. Min Act: -0.0000

Data Index: 1516255 (Python Code)

Max Activating Token Index: 488

Text #6

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.8005. Min Act: -0.0000

Data Index: 1206284 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.7449. Min Act: -0.0000

Data Index: 562484 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.8379. Min Act: -0.0000

Data Index: 1265677 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.8314. Min Act: -0.0000

Data Index: 1630982 (Python Code)

Max Activating Token Index: 502

Text #10

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.7695. Min Act: -0.0000

Data Index: 1367813 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.9168. Min Act: -0.0000

Data Index: 1580897 (Python Code)

Max Activating Token Index: 306

Text #12

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.7206. Min Act: -0.0000

Data Index: 1534229 (Python Code)

Max Activating Token Index: 90

Text #13

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.6095. Min Act: -0.0000

Data Index: 1543693 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.7958. Min Act: -0.0000

Data Index: 1625188 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.7993. Min Act: -0.0000

Data Index: 606792 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.7889. Min Act: -0.0000

Data Index: 9721 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.6760. Min Act: -0.0000

Data Index: 1437997 (Python Code)

Max Activating Token Index: 685

Text #18

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.7801. Min Act: -0.0000

Data Index: 1432226 (Python Code)

Max Activating Token Index: 297

Text #19

Max Range: 2.0967. Min Range: -2.0967

Max Act: 1.8763. Min Act: -0.0000

Data Index: 1502000 (Python Code)

Max Activating Token Index: 264