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

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

Neuron 3304 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.8031. Min Act: -0.0000

Data Index: 510085 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.5219. Min Act: -0.0000

Data Index: 972142 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1233396 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.3731. Min Act: -0.0000

Data Index: 1021929 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.3383. Min Act: -0.0000

Data Index: 167109 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.4115. Min Act: -0.0000

Data Index: 1041661 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.2225. Min Act: -0.0000

Data Index: 533596 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.2415. Min Act: -0.0000

Data Index: 525933 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.2027. Min Act: -0.0000

Data Index: 91224 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.1876. Min Act: -0.0000

Data Index: 140855 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.1599. Min Act: -0.0000

Data Index: 588501 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.1429. Min Act: -0.0000

Data Index: 905220 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1136435 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.0502. Min Act: -0.0000

Data Index: 1184525 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.1343. Min Act: -0.0000

Data Index: 460284 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.0662. Min Act: -0.0000

Data Index: 808035 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.0257. Min Act: -0.0000

Data Index: 1319878 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1343978 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 1.8031. Min Range: -1.8031

Max Act: 0.9979. Min Act: -0.0000

Data Index: 379126 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.8031. Min Range: -1.8031

Max Act: 0.9955. Min Act: -0.0000

Data Index: 377706 (C4 (Web Text))

Max Activating Token Index: 234