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

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

Neuron 4325 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8961. Min Act: 0.0000

Data Index: 1459318 (Python Code)

Max Activating Token Index: 356

Text #1

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6500. Min Act: 0.0000

Data Index: 1539064 (Python Code)

Max Activating Token Index: 744

Text #2

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6560. Min Act: 0.0000

Data Index: 1388308 (Python Code)

Max Activating Token Index: 269

Text #3

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5296. Min Act: 0.0000

Data Index: 1458149 (Python Code)

Max Activating Token Index: 859

Text #4

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1651324 (Python Code)

Max Activating Token Index: 892

Text #5

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6096. Min Act: 0.0000

Data Index: 1648793 (Python Code)

Max Activating Token Index: 460

Text #6

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6282. Min Act: 0.0000

Data Index: 1439980 (Python Code)

Max Activating Token Index: 852

Text #7

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1513513 (Python Code)

Max Activating Token Index: 181

Text #8

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1625849 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5531. Min Act: 0.0001

Data Index: 1637277 (Python Code)

Max Activating Token Index: 794

Text #10

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5574. Min Act: 0.0000

Data Index: 1644672 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1491877 (Python Code)

Max Activating Token Index: 612

Text #12

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5541. Min Act: 0.0001

Data Index: 1395178 (Python Code)

Max Activating Token Index: 404

Text #13

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5349. Min Act: 0.0000

Data Index: 1577774 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.4936. Min Act: 0.0000

Data Index: 1627911 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5266. Min Act: 0.0001

Data Index: 1472528 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5381. Min Act: 0.0000

Data Index: 1459832 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5228. Min Act: -0.0000

Data Index: 836086 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5091. Min Act: 0.0000

Data Index: 1408309 (Python Code)

Max Activating Token Index: 829

Text #19

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.5236. Min Act: 0.0000

Data Index: 1632530 (Python Code)

Max Activating Token Index: 383