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

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

Neuron 4662 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: 2.6102. Min Range: -2.6102

Max Act: 1.9886. Min Act: -0.0000

Data Index: 1527214 (Python Code)

Max Activating Token Index: 454

Text #1

Max Range: 2.6102. Min Range: -2.6102

Max Act: 2.0745. Min Act: -0.0000

Data Index: 1630460 (Python Code)

Max Activating Token Index: 653

Text #2

Max Range: 2.6102. Min Range: -2.6102

Max Act: 2.6102. Min Act: -0.0000

Data Index: 1604503 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 2.6102. Min Range: -2.6102

Max Act: 2.3497. Min Act: -0.0000

Data Index: 1423444 (Python Code)

Max Activating Token Index: 651

Text #4

Max Range: 2.6102. Min Range: -2.6102

Max Act: 2.0707. Min Act: -0.0001

Data Index: 1378093 (Python Code)

Max Activating Token Index: 541

Text #5

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.7958. Min Act: -0.0000

Data Index: 1377051 (Python Code)

Max Activating Token Index: 575

Text #6

Max Range: 2.6102. Min Range: -2.6102

Max Act: 2.0449. Min Act: -0.0000

Data Index: 1384216 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.9122. Min Act: -0.0001

Data Index: 1380584 (Python Code)

Max Activating Token Index: 507

Text #8

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.8604. Min Act: -0.0000

Data Index: 1502995 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.8919. Min Act: -0.0000

Data Index: 1114624 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.8267. Min Act: -0.0001

Data Index: 1525065 (Python Code)

Max Activating Token Index: 228

Text #11

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.9437. Min Act: -0.0000

Data Index: 1386095 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1497082 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.8616. Min Act: -0.0001

Data Index: 1411255 (Python Code)

Max Activating Token Index: 254

Text #14

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.5346. Min Act: -0.0000

Data Index: 1384229 (Python Code)

Max Activating Token Index: 247

Text #15

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.4980. Min Act: -0.0001

Data Index: 1493862 (Python Code)

Max Activating Token Index: 812

Text #16

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.6359. Min Act: -0.0000

Data Index: 1406434 (Python Code)

Max Activating Token Index: 595

Text #17

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.6532. Min Act: -0.0000

Data Index: 958441 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.6354. Min Act: -0.0000

Data Index: 622938 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 2.6102. Min Range: -2.6102

Max Act: 1.4132. Min Act: -0.0000

Data Index: 1228802 (C4 (Web Text))

Max Activating Token Index: 596