Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2178 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6610. Min Act: -0.0004

Data Index: 1635462 (Python Code)

Max Activating Token Index: 168

Text #1

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6746. Min Act: -0.0004

Data Index: 750891 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6968. Min Act: -0.0004

Data Index: 1393162 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6242. Min Act: -0.0004

Data Index: 1530387 (Python Code)

Max Activating Token Index: 589

Text #4

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6362. Min Act: -0.0004

Data Index: 1477014 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5968. Min Act: -0.0004

Data Index: 1409895 (Python Code)

Max Activating Token Index: 323

Text #6

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6214. Min Act: -0.0004

Data Index: 1524146 (Python Code)

Max Activating Token Index: 297

Text #7

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5757. Min Act: -0.0004

Data Index: 1625092 (Python Code)

Max Activating Token Index: 307

Text #8

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5432. Min Act: -0.0004

Data Index: 1428648 (Python Code)

Max Activating Token Index: 526

Text #9

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5405. Min Act: -0.0004

Data Index: 1654637 (Python Code)

Max Activating Token Index: 244

Text #10

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5551. Min Act: -0.0004

Data Index: 1534508 (Python Code)

Max Activating Token Index: 261

Text #11

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5460. Min Act: -0.0004

Data Index: 1513336 (Python Code)

Max Activating Token Index: 787

Text #12

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5255. Min Act: -0.0004

Data Index: 1381527 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5214. Min Act: -0.0004

Data Index: 1478240 (Python Code)

Max Activating Token Index: 832

Text #14

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5295. Min Act: -0.0004

Data Index: 1597095 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5124. Min Act: -0.0004

Data Index: 1466986 (Python Code)

Max Activating Token Index: 157

Text #16

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5095. Min Act: -0.0004

Data Index: 724991 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5262. Min Act: -0.0004

Data Index: 1174171 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.4929. Min Act: -0.0004

Data Index: 1490096 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5098. Min Act: -0.0004

Data Index: 1414464 (Python Code)

Max Activating Token Index: 957