Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 227 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1458652 (Python Code)

Max Activating Token Index: 239

Text #1

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5363. Min Act: 0.0000

Data Index: 1542989 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5330. Min Act: 0.0001

Data Index: 1456139 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1454520 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4725. Min Act: 0.0000

Data Index: 1439521 (Python Code)

Max Activating Token Index: 368

Text #5

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4398. Min Act: 0.0000

Data Index: 1542367 (Python Code)

Max Activating Token Index: 216

Text #6

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4434. Min Act: 0.0001

Data Index: 1622815 (Python Code)

Max Activating Token Index: 615

Text #7

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1636711 (Python Code)

Max Activating Token Index: 377

Text #8

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1533156 (Python Code)

Max Activating Token Index: 465

Text #9

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4573. Min Act: 0.0002

Data Index: 1575140 (Python Code)

Max Activating Token Index: 245

Text #10

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4273. Min Act: 0.0003

Data Index: 1463911 (Python Code)

Max Activating Token Index: 386

Text #11

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4223. Min Act: 0.0000

Data Index: 1435481 (Python Code)

Max Activating Token Index: 336

Text #12

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1485379 (Python Code)

Max Activating Token Index: 714

Text #13

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1627079 (Python Code)

Max Activating Token Index: 463

Text #14

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1364413 (Python Code)

Max Activating Token Index: 141

Text #15

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.3994. Min Act: 0.0002

Data Index: 1543046 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4280. Min Act: 0.0001

Data Index: 1566878 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1392455 (Python Code)

Max Activating Token Index: 71

Text #18

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1564424 (Python Code)

Max Activating Token Index: 680

Text #19

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4116. Min Act: 0.0000

Data Index: 1501773 (Python Code)

Max Activating Token Index: 190