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

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

Neuron 2058 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: 1.4022. Min Range: -1.4022

Max Act: 1.3689. Min Act: -0.0000

Data Index: 1463718 (Python Code)

Max Activating Token Index: 627

Text #1

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2608. Min Act: -0.0000

Data Index: 1657015 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1646819 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2913. Min Act: -0.0000

Data Index: 1539371 (Python Code)

Max Activating Token Index: 154

Text #4

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2891. Min Act: -0.0000

Data Index: 1570278 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2359. Min Act: -0.0000

Data Index: 610535 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1498. Min Act: -0.0000

Data Index: 797204 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1767. Min Act: -0.0000

Data Index: 1453197 (Python Code)

Max Activating Token Index: 827

Text #8

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1008. Min Act: -0.0000

Data Index: 362058 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0616. Min Act: -0.0000

Data Index: 1426897 (Python Code)

Max Activating Token Index: 452

Text #10

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1630916 (Python Code)

Max Activating Token Index: 419

Text #11

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1129. Min Act: -0.0000

Data Index: 725144 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1094190 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0266. Min Act: -0.0000

Data Index: 425205 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9661. Min Act: -0.0000

Data Index: 680139 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9943. Min Act: -0.0000

Data Index: 530072 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1548625 (Python Code)

Max Activating Token Index: 451

Text #17

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1576161 (Python Code)

Max Activating Token Index: 263

Text #18

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9683. Min Act: -0.0000

Data Index: 273119 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1524399 (Python Code)

Max Activating Token Index: 550