Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4001 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2969. Min Act: -0.0000

Data Index: 1511307 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2744. Min Act: -0.0000

Data Index: 1518983 (Python Code)

Max Activating Token Index: 408

Text #2

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1594767 (Python Code)

Max Activating Token Index: 321

Text #3

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1509318 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1381972 (Python Code)

Max Activating Token Index: 336

Text #5

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1554398 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1592132 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2928. Min Act: -0.0000

Data Index: 1483498 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2163. Min Act: -0.0000

Data Index: 1458546 (Python Code)

Max Activating Token Index: 429

Text #9

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2074. Min Act: -0.0000

Data Index: 1575964 (Python Code)

Max Activating Token Index: 490

Text #10

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1504255 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1605422 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1376168 (Python Code)

Max Activating Token Index: 315

Text #13

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1577171 (Python Code)

Max Activating Token Index: 339

Text #14

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1397605 (Python Code)

Max Activating Token Index: 497

Text #15

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0834. Min Act: -0.0000

Data Index: 1390963 (Python Code)

Max Activating Token Index: 591

Text #16

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1540486 (Python Code)

Max Activating Token Index: 598

Text #17

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1529983 (Python Code)

Max Activating Token Index: 121

Text #18

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1651442 (Python Code)

Max Activating Token Index: 932

Text #19

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1465671 (Python Code)

Max Activating Token Index: 200