Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1412 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2167. Min Act: -0.0001

Data Index: 989960 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1055524 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2208. Min Act: -0.0001

Data Index: 350138 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1586160 (Python Code)

Max Activating Token Index: 910

Text #4

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1579985 (Python Code)

Max Activating Token Index: 882

Text #5

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1967. Min Act: -0.0001

Data Index: 360435 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1491943 (Python Code)

Max Activating Token Index: 947

Text #7

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1897. Min Act: -0.0001

Data Index: 108773 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1866. Min Act: -0.0001

Data Index: 476580 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1788. Min Act: -0.0001

Data Index: 402664 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1919. Min Act: -0.0001

Data Index: 297416 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1907. Min Act: -0.0001

Data Index: 510189 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1847. Min Act: -0.0001

Data Index: 588988 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1889. Min Act: -0.0001

Data Index: 1413222 (Python Code)

Max Activating Token Index: 716

Text #14

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1829. Min Act: -0.0001

Data Index: 1415920 (Python Code)

Max Activating Token Index: 296

Text #15

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1702. Min Act: -0.0001

Data Index: 1388333 (Python Code)

Max Activating Token Index: 765

Text #16

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1823. Min Act: -0.0001

Data Index: 1395038 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1702. Min Act: -0.0001

Data Index: 599695 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1817. Min Act: -0.0001

Data Index: 934154 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1802. Min Act: -0.0001

Data Index: 381501 (C4 (Web Text))

Max Activating Token Index: 584