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

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

Neuron 3487 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.7301. Min Act: -0.0001

Data Index: 1504975 (Python Code)

Max Activating Token Index: 660

Text #1

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.6497. Min Act: -0.0001

Data Index: 1375842 (Python Code)

Max Activating Token Index: 945

Text #2

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.6543. Min Act: -0.0001

Data Index: 1580209 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5652. Min Act: -0.0001

Data Index: 1387210 (Python Code)

Max Activating Token Index: 331

Text #4

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5493. Min Act: -0.0001

Data Index: 1600869 (Python Code)

Max Activating Token Index: 818

Text #5

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5389. Min Act: -0.0001

Data Index: 1586276 (Python Code)

Max Activating Token Index: 218

Text #6

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5528. Min Act: -0.0001

Data Index: 1372651 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5171. Min Act: -0.0001

Data Index: 1551001 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4871. Min Act: -0.0001

Data Index: 1541768 (Python Code)

Max Activating Token Index: 662

Text #9

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5024. Min Act: -0.0001

Data Index: 1649844 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5146. Min Act: -0.0001

Data Index: 1388726 (Python Code)

Max Activating Token Index: 221

Text #11

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4974. Min Act: -0.0001

Data Index: 1575071 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4796. Min Act: -0.0001

Data Index: 1482631 (Python Code)

Max Activating Token Index: 966

Text #13

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4485. Min Act: -0.0001

Data Index: 1363729 (Python Code)

Max Activating Token Index: 879

Text #14

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4576. Min Act: -0.0001

Data Index: 1541670 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4758. Min Act: -0.0001

Data Index: 1649727 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4267. Min Act: -0.0001

Data Index: 1598913 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5106. Min Act: -0.0001

Data Index: 1635180 (Python Code)

Max Activating Token Index: 846

Text #18

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1546911 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4438. Min Act: -0.0001

Data Index: 1608797 (Python Code)

Max Activating Token Index: 694