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

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

Neuron 4900 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1589590 (Python Code)

Max Activating Token Index: 431

Text #1

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1445750 (Python Code)

Max Activating Token Index: 523

Text #2

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1407125 (Python Code)

Max Activating Token Index: 741

Text #3

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1504510 (Python Code)

Max Activating Token Index: 531

Text #4

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1636855 (Python Code)

Max Activating Token Index: 411

Text #5

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1991. Min Act: -0.0000

Data Index: 568172 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1559859 (Python Code)

Max Activating Token Index: 429

Text #7

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1490561 (Python Code)

Max Activating Token Index: 911

Text #8

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1450520 (Python Code)

Max Activating Token Index: 666

Text #9

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1450618 (Python Code)

Max Activating Token Index: 443

Text #10

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1485045 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1700. Min Act: -0.0000

Data Index: 755248 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1607625 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1369010 (Python Code)

Max Activating Token Index: 520

Text #14

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1571. Min Act: -0.0000

Data Index: 713872 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1586464 (Python Code)

Max Activating Token Index: 311

Text #16

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1220953 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1134708 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1394673 (Python Code)

Max Activating Token Index: 178

Text #19

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1440050 (Python Code)

Max Activating Token Index: 405