Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3061 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0283. Min Range: -1.0283

Max Act: 1.0283. Min Act: -0.0001

Data Index: 1645527 (Python Code)

Max Activating Token Index: 516

Text #1

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8646. Min Act: -0.0001

Data Index: 1512365 (Python Code)

Max Activating Token Index: 141

Text #2

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7917. Min Act: -0.0001

Data Index: 635430 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1194973 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7680. Min Act: -0.0001

Data Index: 1528498 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7365. Min Act: -0.0001

Data Index: 1556938 (Python Code)

Max Activating Token Index: 883

Text #6

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7393. Min Act: -0.0001

Data Index: 1372453 (Python Code)

Max Activating Token Index: 538

Text #7

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7814. Min Act: -0.0001

Data Index: 475018 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7616. Min Act: -0.0001

Data Index: 1483544 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7588. Min Act: -0.0001

Data Index: 919291 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7224. Min Act: -0.0001

Data Index: 730202 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7721. Min Act: -0.0001

Data Index: 1634907 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7178. Min Act: -0.0001

Data Index: 813281 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7297. Min Act: -0.0001

Data Index: 1038349 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7208. Min Act: -0.0001

Data Index: 1286081 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.6675. Min Act: -0.0001

Data Index: 1510417 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.6574. Min Act: -0.0001

Data Index: 1435329 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7530. Min Act: -0.0001

Data Index: 1445019 (Python Code)

Max Activating Token Index: 454

Text #18

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.6922. Min Act: -0.0001

Data Index: 1435696 (Python Code)

Max Activating Token Index: 268

Text #19

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7157. Min Act: -0.0001

Data Index: 144214 (C4 (Web Text))

Max Activating Token Index: 741