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

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

Neuron 3353 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1900. Min Act: -0.0001

Data Index: 1078537 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1730. Min Act: -0.0001

Data Index: 584540 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1708. Min Act: -0.0001

Data Index: 658139 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1800. Min Act: -0.0001

Data Index: 1140902 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1563. Min Act: -0.0001

Data Index: 1265893 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1791. Min Act: -0.0001

Data Index: 379837 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1594. Min Act: -0.0001

Data Index: 499289 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1801. Min Act: -0.0001

Data Index: 1321936 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1547. Min Act: -0.0001

Data Index: 597018 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1439. Min Act: -0.0001

Data Index: 174960 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1450. Min Act: -0.0001

Data Index: 740341 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1511. Min Act: -0.0001

Data Index: 993877 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1445. Min Act: -0.0001

Data Index: 1603651 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1538. Min Act: -0.0001

Data Index: 70665 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1513. Min Act: -0.0001

Data Index: 891910 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1337. Min Act: -0.0001

Data Index: 921351 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1503. Min Act: -0.0001

Data Index: 1141079 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1575. Min Act: -0.0001

Data Index: 590684 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1462. Min Act: -0.0001

Data Index: 869008 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1295. Min Act: -0.0001

Data Index: 412803 (C4 (Web Text))

Max Activating Token Index: 980