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

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

Neuron 3511 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: 5.3928. Min Range: -5.3928

Max Act: 5.3928. Min Act: -0.0000

Data Index: 1397801 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 5.3928. Min Range: -5.3928

Max Act: 3.9056. Min Act: -0.0000

Data Index: 232141 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 5.3928. Min Range: -5.3928

Max Act: 3.3810. Min Act: -0.0000

Data Index: 1528490 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.9206. Min Act: -0.0000

Data Index: 1602018 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 5.3928. Min Range: -5.3928

Max Act: 3.0537. Min Act: -0.0000

Data Index: 1413444 (Python Code)

Max Activating Token Index: 522

Text #5

Max Range: 5.3928. Min Range: -5.3928

Max Act: 3.0269. Min Act: -0.0000

Data Index: 1460577 (Python Code)

Max Activating Token Index: 118

Text #6

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.9566. Min Act: -0.0000

Data Index: 1329353 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.3790. Min Act: -0.0000

Data Index: 1585897 (Python Code)

Max Activating Token Index: 393

Text #8

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.6428. Min Act: -0.0000

Data Index: 1369624 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.6198. Min Act: -0.0000

Data Index: 1529712 (Python Code)

Max Activating Token Index: 611

Text #10

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.5890. Min Act: -0.0000

Data Index: 1600948 (Python Code)

Max Activating Token Index: 465

Text #11

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.3390. Min Act: -0.0000

Data Index: 1503601 (Python Code)

Max Activating Token Index: 750

Text #12

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.5338. Min Act: -0.0000

Data Index: 1613006 (Python Code)

Max Activating Token Index: 603

Text #13

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.3880. Min Act: -0.0000

Data Index: 1534354 (Python Code)

Max Activating Token Index: 773

Text #14

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.2994. Min Act: -0.0000

Data Index: 1461706 (Python Code)

Max Activating Token Index: 17

Text #15

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.2532. Min Act: -0.0000

Data Index: 1363664 (Python Code)

Max Activating Token Index: 818

Text #16

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.3669. Min Act: -0.0000

Data Index: 1573857 (Python Code)

Max Activating Token Index: 401

Text #17

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.4591. Min Act: -0.0000

Data Index: 1487201 (Python Code)

Max Activating Token Index: 883

Text #18

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.1881. Min Act: -0.0000

Data Index: 1586966 (Python Code)

Max Activating Token Index: 404

Text #19

Max Range: 5.3928. Min Range: -5.3928

Max Act: 2.1455. Min Act: -0.0000

Data Index: 1491264 (Python Code)

Max Activating Token Index: 587