Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1850 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.8031. Min Act: -0.0001

Data Index: 1499615 (Python Code)

Max Activating Token Index: 755

Text #1

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7350. Min Act: -0.0001

Data Index: 1530074 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7376. Min Act: -0.0001

Data Index: 1377207 (Python Code)

Max Activating Token Index: 88

Text #3

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7211. Min Act: -0.0001

Data Index: 1431593 (Python Code)

Max Activating Token Index: 748

Text #4

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7443. Min Act: -0.0001

Data Index: 1361184 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7349. Min Act: -0.0001

Data Index: 1650220 (Python Code)

Max Activating Token Index: 375

Text #6

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7231. Min Act: -0.0001

Data Index: 1530680 (Python Code)

Max Activating Token Index: 975

Text #7

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7018. Min Act: -0.0001

Data Index: 1490268 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6660. Min Act: -0.0001

Data Index: 1423333 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6878. Min Act: -0.0001

Data Index: 1655512 (Python Code)

Max Activating Token Index: 232

Text #10

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6643. Min Act: -0.0001

Data Index: 1369696 (Python Code)

Max Activating Token Index: 696

Text #11

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7235. Min Act: -0.0001

Data Index: 1564126 (Python Code)

Max Activating Token Index: 974

Text #12

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7617. Min Act: -0.0001

Data Index: 1394881 (Python Code)

Max Activating Token Index: 348

Text #13

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6890. Min Act: -0.0001

Data Index: 1440288 (Python Code)

Max Activating Token Index: 999

Text #14

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6893. Min Act: -0.0001

Data Index: 1427755 (Python Code)

Max Activating Token Index: 332

Text #15

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6899. Min Act: -0.0001

Data Index: 1360063 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6692. Min Act: -0.0001

Data Index: 1379254 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6486. Min Act: -0.0001

Data Index: 1446951 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6843. Min Act: -0.0001

Data Index: 1531602 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7082. Min Act: -0.0001

Data Index: 1448228 (Python Code)

Max Activating Token Index: 929