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

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

Neuron 3953 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: 5.4873. Min Range: -5.4873

Max Act: 5.2653. Min Act: -0.0000

Data Index: 1559471 (Python Code)

Max Activating Token Index: 327

Text #1

Max Range: 5.4873. Min Range: -5.4873

Max Act: 5.4873. Min Act: -0.0000

Data Index: 1588446 (Python Code)

Max Activating Token Index: 550

Text #2

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.9167. Min Act: -0.0000

Data Index: 1606230 (Python Code)

Max Activating Token Index: 316

Text #3

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.8562. Min Act: -0.0000

Data Index: 1617356 (Python Code)

Max Activating Token Index: 458

Text #4

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.9100. Min Act: -0.0000

Data Index: 1590979 (Python Code)

Max Activating Token Index: 285

Text #5

Max Range: 5.4873. Min Range: -5.4873

Max Act: 5.0321. Min Act: -0.0000

Data Index: 1637219 (Python Code)

Max Activating Token Index: 497

Text #6

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.4324. Min Act: -0.0000

Data Index: 1592754 (Python Code)

Max Activating Token Index: 252

Text #7

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.6038. Min Act: -0.0000

Data Index: 1563805 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.7730. Min Act: -0.0000

Data Index: 1399030 (Python Code)

Max Activating Token Index: 304

Text #9

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.7508. Min Act: -0.0000

Data Index: 1607965 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.6851. Min Act: -0.0000

Data Index: 1636622 (Python Code)

Max Activating Token Index: 244

Text #11

Max Range: 5.4873. Min Range: -5.4873

Max Act: 5.0017. Min Act: -0.0000

Data Index: 1494066 (Python Code)

Max Activating Token Index: 230

Text #12

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.8217. Min Act: -0.0000

Data Index: 1547351 (Python Code)

Max Activating Token Index: 328

Text #13

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.7517. Min Act: -0.0000

Data Index: 1632163 (Python Code)

Max Activating Token Index: 615

Text #14

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.7115. Min Act: -0.0000

Data Index: 1605322 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.6983. Min Act: -0.0000

Data Index: 1433762 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.4705. Min Act: -0.0000

Data Index: 1638465 (Python Code)

Max Activating Token Index: 716

Text #17

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.0168. Min Act: -0.0000

Data Index: 1637572 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.5488. Min Act: -0.0000

Data Index: 1635750 (Python Code)

Max Activating Token Index: 577

Text #19

Max Range: 5.4873. Min Range: -5.4873

Max Act: 4.5346. Min Act: -0.0000

Data Index: 1510195 (Python Code)

Max Activating Token Index: 710