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

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

Neuron 4294 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.5070. Min Act: -0.0000

Data Index: 1638230 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1486384 (Python Code)

Max Activating Token Index: 293

Text #2

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.3576. Min Act: -0.0000

Data Index: 1562557 (Python Code)

Max Activating Token Index: 264

Text #3

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.3652. Min Act: -0.0000

Data Index: 1436934 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.2896. Min Act: -0.0000

Data Index: 1616924 (Python Code)

Max Activating Token Index: 131

Text #5

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1474563 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.3280. Min Act: -0.0000

Data Index: 1381717 (Python Code)

Max Activating Token Index: 997

Text #7

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1574351 (Python Code)

Max Activating Token Index: 224

Text #8

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1876. Min Act: -0.0000

Data Index: 1612637 (Python Code)

Max Activating Token Index: 171

Text #9

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1593917 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.2035. Min Act: -0.0000

Data Index: 1375503 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1372693 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1634. Min Act: -0.0000

Data Index: 1506643 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1398. Min Act: -0.0000

Data Index: 290118 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1382316 (Python Code)

Max Activating Token Index: 979

Text #15

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1206. Min Act: -0.0000

Data Index: 451267 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1443725 (Python Code)

Max Activating Token Index: 196

Text #17

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1652227 (Python Code)

Max Activating Token Index: 951

Text #18

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1338. Min Act: -0.0000

Data Index: 686207 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.0992. Min Act: -0.0000

Data Index: 1397327 (Python Code)

Max Activating Token Index: 867