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

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

Neuron 2247 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2227. Min Range: -2.2227

Max Act: 2.2227. Min Act: -0.0000

Data Index: 1597453 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.7848. Min Act: -0.0000

Data Index: 1488210 (Python Code)

Max Activating Token Index: 279

Text #2

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.7392. Min Act: -0.0000

Data Index: 1171868 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.7361. Min Act: -0.0000

Data Index: 1507963 (Python Code)

Max Activating Token Index: 150

Text #4

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.5437. Min Act: -0.0000

Data Index: 1481255 (Python Code)

Max Activating Token Index: 558

Text #5

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.5328. Min Act: -0.0000

Data Index: 1361242 (Python Code)

Max Activating Token Index: 803

Text #6

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1537873 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.3893. Min Act: -0.0000

Data Index: 1601601 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1506889 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.4625. Min Act: -0.0000

Data Index: 1656927 (Python Code)

Max Activating Token Index: 500

Text #10

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.3924. Min Act: -0.0000

Data Index: 1528663 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.5306. Min Act: -0.0000

Data Index: 1588335 (Python Code)

Max Activating Token Index: 199

Text #12

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.4962. Min Act: -0.0000

Data Index: 1504763 (Python Code)

Max Activating Token Index: 736

Text #13

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1551844 (Python Code)

Max Activating Token Index: 624

Text #14

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1612210 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1569981 (Python Code)

Max Activating Token Index: 640

Text #16

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.3316. Min Act: -0.0000

Data Index: 1535266 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.2940. Min Act: -0.0000

Data Index: 1489900 (Python Code)

Max Activating Token Index: 861

Text #18

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.2156. Min Act: -0.0000

Data Index: 1654885 (Python Code)

Max Activating Token Index: 612

Text #19

Max Range: 2.2227. Min Range: -2.2227

Max Act: 1.2409. Min Act: -0.0000

Data Index: 1606911 (Python Code)

Max Activating Token Index: 851