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

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

Neuron 47 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: 0.6100. Min Range: -0.6100

Max Act: 0.5736. Min Act: -0.0001

Data Index: 1637232 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5834. Min Act: -0.0001

Data Index: 1567776 (Python Code)

Max Activating Token Index: 108

Text #2

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.6002. Min Act: -0.0001

Data Index: 1463261 (Python Code)

Max Activating Token Index: 970

Text #3

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5954. Min Act: -0.0001

Data Index: 1581392 (Python Code)

Max Activating Token Index: 306

Text #4

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5751. Min Act: -0.0001

Data Index: 1540182 (Python Code)

Max Activating Token Index: 212

Text #5

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5752. Min Act: -0.0001

Data Index: 597945 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1405207 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5529. Min Act: -0.0001

Data Index: 1596751 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.6100. Min Act: -0.0001

Data Index: 1434603 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5419. Min Act: -0.0001

Data Index: 1415078 (Python Code)

Max Activating Token Index: 308

Text #10

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4928. Min Act: -0.0001

Data Index: 1462335 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5032. Min Act: -0.0001

Data Index: 1533419 (Python Code)

Max Activating Token Index: 294

Text #12

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5237. Min Act: -0.0001

Data Index: 1551126 (Python Code)

Max Activating Token Index: 234

Text #13

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5532. Min Act: -0.0001

Data Index: 1616030 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5177. Min Act: -0.0001

Data Index: 1381340 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5388. Min Act: -0.0001

Data Index: 1613231 (Python Code)

Max Activating Token Index: 274

Text #16

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5520. Min Act: -0.0001

Data Index: 1533586 (Python Code)

Max Activating Token Index: 410

Text #17

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5703. Min Act: -0.0001

Data Index: 1387297 (Python Code)

Max Activating Token Index: 857

Text #18

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5529. Min Act: -0.0001

Data Index: 1432133 (Python Code)

Max Activating Token Index: 440

Text #19

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5659. Min Act: -0.0001

Data Index: 416162 (C4 (Web Text))

Max Activating Token Index: 1000