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

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

Neuron 1051 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2984. Min Act: -0.0003

Data Index: 1400224 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.3103. Min Act: -0.0003

Data Index: 1525471 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2877. Min Act: -0.0003

Data Index: 1537488 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2627. Min Act: -0.0003

Data Index: 1456093 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2285. Min Act: -0.0003

Data Index: 1649153 (Python Code)

Max Activating Token Index: 858

Text #5

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2671. Min Act: -0.0003

Data Index: 1525918 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2522. Min Act: -0.0003

Data Index: 1369107 (Python Code)

Max Activating Token Index: 364

Text #7

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2913. Min Act: -0.0003

Data Index: 1641602 (Python Code)

Max Activating Token Index: 80

Text #8

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2791. Min Act: -0.0003

Data Index: 1527289 (Python Code)

Max Activating Token Index: 704

Text #9

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2782. Min Act: -0.0003

Data Index: 1499185 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2584. Min Act: -0.0003

Data Index: 1463713 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2479. Min Act: -0.0003

Data Index: 1564248 (Python Code)

Max Activating Token Index: 978

Text #12

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2686. Min Act: -0.0003

Data Index: 1580168 (Python Code)

Max Activating Token Index: 652

Text #13

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2454. Min Act: -0.0003

Data Index: 1510315 (Python Code)

Max Activating Token Index: 398

Text #14

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2726. Min Act: -0.0003

Data Index: 1565021 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2409. Min Act: -0.0003

Data Index: 1519704 (Python Code)

Max Activating Token Index: 824

Text #16

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2892. Min Act: -0.0003

Data Index: 1434967 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2571. Min Act: -0.0003

Data Index: 1575885 (Python Code)

Max Activating Token Index: 919

Text #18

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2887. Min Act: -0.0003

Data Index: 1647338 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2663. Min Act: -0.0003

Data Index: 1629228 (Python Code)

Max Activating Token Index: 367