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

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

Neuron 2421 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0031. Min Act: -0.0002

Data Index: 1327744 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0032. Min Act: -0.0002

Data Index: 995527 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1435422 (Python Code)

Max Activating Token Index: 429

Text #3

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1432410 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0002

Data Index: 1448242 (Python Code)

Max Activating Token Index: 515

Text #5

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0026. Min Act: -0.0002

Data Index: 171040 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1433746 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1560897 (Python Code)

Max Activating Token Index: 683

Text #8

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1437963 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1583834 (Python Code)

Max Activating Token Index: 366

Text #10

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1650542 (Python Code)

Max Activating Token Index: 676

Text #11

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1127133 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1622225 (Python Code)

Max Activating Token Index: 447

Text #13

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1621259 (Python Code)

Max Activating Token Index: 536

Text #14

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0002

Data Index: 240239 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1433621 (Python Code)

Max Activating Token Index: 464

Text #16

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0023. Min Act: -0.0002

Data Index: 1485182 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0002

Data Index: 464917 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1455182 (Python Code)

Max Activating Token Index: 392

Text #19

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1545019 (Python Code)

Max Activating Token Index: 214