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

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

Neuron 1143 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: 3.8346. Min Range: -3.8346

Max Act: 3.8346. Min Act: -0.0000

Data Index: 1488219 (Python Code)

Max Activating Token Index: 812

Text #1

Max Range: 3.8346. Min Range: -3.8346

Max Act: 3.0284. Min Act: -0.0000

Data Index: 969012 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.8892. Min Act: -0.0000

Data Index: 1442458 (Python Code)

Max Activating Token Index: 482

Text #3

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.9042. Min Act: -0.0000

Data Index: 1487723 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.8215. Min Act: -0.0000

Data Index: 1485328 (Python Code)

Max Activating Token Index: 748

Text #5

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.6632. Min Act: -0.0000

Data Index: 1420935 (Python Code)

Max Activating Token Index: 646

Text #6

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.5180. Min Act: -0.0000

Data Index: 454690 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.8761. Min Act: -0.0000

Data Index: 1632647 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.8571. Min Act: -0.0000

Data Index: 1073 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.7257. Min Act: -0.0000

Data Index: 1482159 (Python Code)

Max Activating Token Index: 317

Text #10

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.5383. Min Act: -0.0000

Data Index: 1424458 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.6651. Min Act: -0.0000

Data Index: 1335893 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.6622. Min Act: -0.0000

Data Index: 1615767 (Python Code)

Max Activating Token Index: 500

Text #13

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.7386. Min Act: -0.0000

Data Index: 29498 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.5912. Min Act: -0.0000

Data Index: 649283 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.5647. Min Act: -0.0000

Data Index: 170909 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.5426. Min Act: -0.0000

Data Index: 516686 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.4026. Min Act: -0.0000

Data Index: 1426407 (Python Code)

Max Activating Token Index: 734

Text #18

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.3846. Min Act: -0.0000

Data Index: 1480187 (Python Code)

Max Activating Token Index: 327

Text #19

Max Range: 3.8346. Min Range: -3.8346

Max Act: 2.3804. Min Act: -0.0000

Data Index: 305322 (C4 (Web Text))

Max Activating Token Index: 553