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

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

Neuron 908 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: 0.7196. Min Range: -0.7196

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1594930 (Python Code)

Max Activating Token Index: 898

Text #1

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.7177. Min Act: -0.0000

Data Index: 1500611 (Python Code)

Max Activating Token Index: 195

Text #2

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1377063 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1497851 (Python Code)

Max Activating Token Index: 581

Text #4

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1491276 (Python Code)

Max Activating Token Index: 238

Text #5

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1544291 (Python Code)

Max Activating Token Index: 811

Text #6

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1438459 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1636064 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1621753 (Python Code)

Max Activating Token Index: 290

Text #9

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1647930 (Python Code)

Max Activating Token Index: 818

Text #10

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1509147 (Python Code)

Max Activating Token Index: 180

Text #11

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1360622 (Python Code)

Max Activating Token Index: 599

Text #12

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1403227 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5982. Min Act: -0.0000

Data Index: 259667 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1589411 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1517282 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5408. Min Act: -0.0000

Data Index: 132361 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1459571 (Python Code)

Max Activating Token Index: 252

Text #18

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5316. Min Act: -0.0000

Data Index: 476636 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1548532 (Python Code)

Max Activating Token Index: 706