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

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

Neuron 5656 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7009. Min Range: -4.7009

Max Act: 4.7009. Min Act: -0.0000

Data Index: 1482918 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 4.7009. Min Range: -4.7009

Max Act: 4.4260. Min Act: -0.0000

Data Index: 1542696 (Python Code)

Max Activating Token Index: 918

Text #2

Max Range: 4.7009. Min Range: -4.7009

Max Act: 4.1863. Min Act: -0.0000

Data Index: 1443961 (Python Code)

Max Activating Token Index: 311

Text #3

Max Range: 4.7009. Min Range: -4.7009

Max Act: 4.1953. Min Act: -0.0000

Data Index: 1407893 (Python Code)

Max Activating Token Index: 483

Text #4

Max Range: 4.7009. Min Range: -4.7009

Max Act: 4.1245. Min Act: -0.0000

Data Index: 1563034 (Python Code)

Max Activating Token Index: 53

Text #5

Max Range: 4.7009. Min Range: -4.7009

Max Act: 4.1210. Min Act: -0.0000

Data Index: 1436645 (Python Code)

Max Activating Token Index: 785

Text #6

Max Range: 4.7009. Min Range: -4.7009

Max Act: 4.0839. Min Act: -0.0000

Data Index: 1627659 (Python Code)

Max Activating Token Index: 922

Text #7

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.4652. Min Act: -0.0000

Data Index: 1259018 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.8662. Min Act: -0.0000

Data Index: 514207 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.5423. Min Act: -0.0000

Data Index: 443107 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.5358. Min Act: -0.0000

Data Index: 1557389 (Python Code)

Max Activating Token Index: 541

Text #11

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.5157. Min Act: -0.0000

Data Index: 1397774 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.6730. Min Act: -0.0000

Data Index: 1400175 (Python Code)

Max Activating Token Index: 201

Text #13

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.4967. Min Act: -0.0000

Data Index: 1552824 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.6029. Min Act: -0.0000

Data Index: 1639808 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.7650. Min Act: -0.0000

Data Index: 1552762 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.4577. Min Act: -0.0000

Data Index: 1637107 (Python Code)

Max Activating Token Index: 285

Text #17

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.3231. Min Act: -0.0000

Data Index: 1366621 (Python Code)

Max Activating Token Index: 299

Text #18

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.5653. Min Act: -0.0000

Data Index: 1467923 (Python Code)

Max Activating Token Index: 880

Text #19

Max Range: 4.7009. Min Range: -4.7009

Max Act: 3.7372. Min Act: -0.0000

Data Index: 1372403 (Python Code)

Max Activating Token Index: 665