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

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

Neuron 3833 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.5394. Min Act: -0.0001

Data Index: 1301390 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1289108 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3224. Min Act: -0.0000

Data Index: 309604 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3321. Min Act: -0.0001

Data Index: 1380817 (Python Code)

Max Activating Token Index: 115

Text #4

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3534. Min Act: -0.0000

Data Index: 898005 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1583284 (Python Code)

Max Activating Token Index: 536

Text #6

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1495610 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2909. Min Act: -0.0001

Data Index: 1517243 (Python Code)

Max Activating Token Index: 633

Text #8

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1591951 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1525693 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1559467 (Python Code)

Max Activating Token Index: 221

Text #11

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1548112 (Python Code)

Max Activating Token Index: 359

Text #12

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1442326 (Python Code)

Max Activating Token Index: 568

Text #13

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2846. Min Act: -0.0001

Data Index: 1425983 (Python Code)

Max Activating Token Index: 296

Text #14

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1605165 (Python Code)

Max Activating Token Index: 942

Text #15

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1437271 (Python Code)

Max Activating Token Index: 838

Text #16

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1498023 (Python Code)

Max Activating Token Index: 324

Text #17

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1428093 (Python Code)

Max Activating Token Index: 291

Text #18

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1540058 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1406990 (Python Code)

Max Activating Token Index: 347