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

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

Neuron 5741 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0351. Min Range: -3.0351

Max Act: 3.0351. Min Act: 0.0000

Data Index: 1512683 (Python Code)

Max Activating Token Index: 471

Text #1

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.4841. Min Act: 0.0000

Data Index: 1607733 (Python Code)

Max Activating Token Index: 893

Text #2

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.4406. Min Act: 0.0000

Data Index: 1453760 (Python Code)

Max Activating Token Index: 132

Text #3

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.4335. Min Act: -0.0000

Data Index: 1528347 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.3654. Min Act: 0.0000

Data Index: 1645554 (Python Code)

Max Activating Token Index: 104

Text #5

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.3520. Min Act: 0.0000

Data Index: 80875 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.2313. Min Act: 0.0000

Data Index: 1392741 (Python Code)

Max Activating Token Index: 128

Text #7

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.1619. Min Act: 0.0000

Data Index: 1449828 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.1912. Min Act: 0.0000

Data Index: 1402607 (Python Code)

Max Activating Token Index: 203

Text #9

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.0755. Min Act: -0.0000

Data Index: 1592172 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.0318. Min Act: 0.0000

Data Index: 1457392 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 3.0351. Min Range: -3.0351

Max Act: 1.9152. Min Act: 0.0000

Data Index: 1539262 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.0025. Min Act: 0.0000

Data Index: 1371431 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.0087. Min Act: 0.0000

Data Index: 1436627 (Python Code)

Max Activating Token Index: 209

Text #14

Max Range: 3.0351. Min Range: -3.0351

Max Act: 2.0029. Min Act: 0.0000

Data Index: 1464517 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 3.0351. Min Range: -3.0351

Max Act: 1.8814. Min Act: -0.0000

Data Index: 286369 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 3.0351. Min Range: -3.0351

Max Act: 1.9383. Min Act: -0.0000

Data Index: 518343 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 3.0351. Min Range: -3.0351

Max Act: 1.7026. Min Act: 0.0000

Data Index: 473168 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 3.0351. Min Range: -3.0351

Max Act: 1.8780. Min Act: 0.0000

Data Index: 1383203 (Python Code)

Max Activating Token Index: 407

Text #19

Max Range: 3.0351. Min Range: -3.0351

Max Act: 1.8703. Min Act: -0.0000

Data Index: 1328312 (C4 (Web Text))

Max Activating Token Index: 293