Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3914 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0786. Min Range: -4.0786

Max Act: 4.0786. Min Act: -0.0000

Data Index: 1429584 (Python Code)

Max Activating Token Index: 278

Text #1

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.8966. Min Act: -0.0000

Data Index: 1484136 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.4397. Min Act: -0.0000

Data Index: 1637276 (Python Code)

Max Activating Token Index: 480

Text #3

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.7238. Min Act: -0.0000

Data Index: 1548768 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.6806. Min Act: -0.0000

Data Index: 1615472 (Python Code)

Max Activating Token Index: 267

Text #5

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.6777. Min Act: -0.0000

Data Index: 1444471 (Python Code)

Max Activating Token Index: 378

Text #6

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.1727. Min Act: -0.0000

Data Index: 1472761 (Python Code)

Max Activating Token Index: 307

Text #7

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.3096. Min Act: -0.0000

Data Index: 1566371 (Python Code)

Max Activating Token Index: 528

Text #8

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.2763. Min Act: -0.0000

Data Index: 1468725 (Python Code)

Max Activating Token Index: 363

Text #9

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.7018. Min Act: -0.0000

Data Index: 1375800 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.2978. Min Act: -0.0000

Data Index: 1642077 (Python Code)

Max Activating Token Index: 346

Text #11

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.3412. Min Act: -0.0000

Data Index: 1625222 (Python Code)

Max Activating Token Index: 265

Text #12

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.3289. Min Act: -0.0000

Data Index: 1395303 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.1650. Min Act: -0.0000

Data Index: 1369005 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.0357. Min Act: -0.0000

Data Index: 1618857 (Python Code)

Max Activating Token Index: 357

Text #15

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.0397. Min Act: -0.0000

Data Index: 1427455 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.3251. Min Act: -0.0000

Data Index: 1403297 (Python Code)

Max Activating Token Index: 263

Text #17

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.4022. Min Act: -0.0000

Data Index: 1529956 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 4.0786. Min Range: -4.0786

Max Act: 3.1290. Min Act: -0.0000

Data Index: 1430569 (Python Code)

Max Activating Token Index: 506

Text #19

Max Range: 4.0786. Min Range: -4.0786

Max Act: 2.9727. Min Act: -0.0000

Data Index: 1462587 (Python Code)

Max Activating Token Index: 368