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

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

Neuron 669 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3474. Min Act: -0.0000

Data Index: 435511 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1458199 (Python Code)

Max Activating Token Index: 346

Text #2

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1599660 (Python Code)

Max Activating Token Index: 206

Text #3

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3075. Min Act: -0.0000

Data Index: 351009 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3168. Min Act: -0.0000

Data Index: 243564 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3048. Min Act: -0.0000

Data Index: 803056 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1441753 (Python Code)

Max Activating Token Index: 382

Text #7

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1546438 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1639435 (Python Code)

Max Activating Token Index: 214

Text #9

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1448362 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1531825 (Python Code)

Max Activating Token Index: 750

Text #11

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1495294 (Python Code)

Max Activating Token Index: 388

Text #12

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1587614 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1441896 (Python Code)

Max Activating Token Index: 385

Text #14

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1547655 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2838. Min Act: -0.0000

Data Index: 606168 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1361739 (Python Code)

Max Activating Token Index: 317

Text #17

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1630061 (Python Code)

Max Activating Token Index: 710

Text #18

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1510745 (Python Code)

Max Activating Token Index: 548

Text #19

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1657075 (Python Code)

Max Activating Token Index: 391