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

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

Neuron 1050 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.7988. Min Act: -0.0000

Data Index: 1586433 (Python Code)

Max Activating Token Index: 658

Text #1

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6256. Min Act: -0.0000

Data Index: 1449523 (Python Code)

Max Activating Token Index: 552

Text #2

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.4002. Min Act: -0.0000

Data Index: 1545786 (Python Code)

Max Activating Token Index: 289

Text #3

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6649. Min Act: -0.0000

Data Index: 1503868 (Python Code)

Max Activating Token Index: 705

Text #4

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.2433. Min Act: -0.0000

Data Index: 1395860 (Python Code)

Max Activating Token Index: 262

Text #5

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.2069. Min Act: -0.0000

Data Index: 1387133 (Python Code)

Max Activating Token Index: 652

Text #6

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.1874. Min Act: -0.0000

Data Index: 1451010 (Python Code)

Max Activating Token Index: 807

Text #7

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.2942. Min Act: -0.0000

Data Index: 1376998 (Python Code)

Max Activating Token Index: 1005

Text #8

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.2777. Min Act: -0.0000

Data Index: 1523733 (Python Code)

Max Activating Token Index: 432

Text #9

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.1522. Min Act: -0.0000

Data Index: 1494027 (Python Code)

Max Activating Token Index: 574

Text #10

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.1441. Min Act: -0.0000

Data Index: 1361591 (Python Code)

Max Activating Token Index: 300

Text #11

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.1229. Min Act: -0.0000

Data Index: 1363950 (Python Code)

Max Activating Token Index: 1011

Text #12

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.3166. Min Act: 0.0000

Data Index: 1473963 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.2695. Min Act: -0.0000

Data Index: 1505660 (Python Code)

Max Activating Token Index: 640

Text #14

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.1341. Min Act: -0.0000

Data Index: 1566639 (Python Code)

Max Activating Token Index: 693

Text #15

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.1322. Min Act: -0.0000

Data Index: 1588355 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.2232. Min Act: -0.0000

Data Index: 1634319 (Python Code)

Max Activating Token Index: 675

Text #17

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.2262. Min Act: -0.0000

Data Index: 1436021 (Python Code)

Max Activating Token Index: 253

Text #18

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.2944. Min Act: -0.0000

Data Index: 1573299 (Python Code)

Max Activating Token Index: 912

Text #19

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.0278. Min Act: -0.0000

Data Index: 1462469 (Python Code)

Max Activating Token Index: 336