Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2907 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4394. Min Act: -0.0001

Data Index: 1601175 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4211. Min Act: -0.0001

Data Index: 976249 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3585. Min Act: -0.0001

Data Index: 1013594 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3728. Min Act: -0.0001

Data Index: 944280 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3478. Min Act: -0.0001

Data Index: 745503 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3550. Min Act: -0.0001

Data Index: 5314 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3446. Min Act: -0.0001

Data Index: 349778 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3512. Min Act: -0.0001

Data Index: 1596584 (Python Code)

Max Activating Token Index: 1009

Text #8

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3712. Min Act: -0.0000

Data Index: 591684 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3446. Min Act: -0.0001

Data Index: 1531301 (Python Code)

Max Activating Token Index: 865

Text #10

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3417. Min Act: -0.0001

Data Index: 1635361 (Python Code)

Max Activating Token Index: 263

Text #11

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3504. Min Act: -0.0001

Data Index: 1498423 (Python Code)

Max Activating Token Index: 920

Text #12

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1351774 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3422. Min Act: -0.0001

Data Index: 1558310 (Python Code)

Max Activating Token Index: 764

Text #14

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2923. Min Act: -0.0001

Data Index: 1415571 (Python Code)

Max Activating Token Index: 997

Text #15

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1233253 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3222. Min Act: -0.0001

Data Index: 1635033 (Python Code)

Max Activating Token Index: 825

Text #17

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3033. Min Act: -0.0001

Data Index: 1133247 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3073. Min Act: -0.0001

Data Index: 1393865 (Python Code)

Max Activating Token Index: 1004

Text #19

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3010. Min Act: -0.0001

Data Index: 1588660 (Python Code)

Max Activating Token Index: 626