Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4055 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1380024 (Python Code)

Max Activating Token Index: 457

Text #1

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1625213 (Python Code)

Max Activating Token Index: 824

Text #2

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1496051 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1613271 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1490582 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1520393 (Python Code)

Max Activating Token Index: 541

Text #6

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1543947 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1622394 (Python Code)

Max Activating Token Index: 367

Text #8

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1406056 (Python Code)

Max Activating Token Index: 642

Text #9

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1551142 (Python Code)

Max Activating Token Index: 417

Text #10

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1517370 (Python Code)

Max Activating Token Index: 986

Text #11

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1433294 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1499255 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1592858 (Python Code)

Max Activating Token Index: 824

Text #14

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1589215 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1596938 (Python Code)

Max Activating Token Index: 993

Text #16

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1407324 (Python Code)

Max Activating Token Index: 862

Text #17

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1436632 (Python Code)

Max Activating Token Index: 854

Text #18

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1527182 (Python Code)

Max Activating Token Index: 342

Text #19

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1547101 (Python Code)

Max Activating Token Index: 762