Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2931 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3577. Min Act: -0.0003

Data Index: 1548318 (Python Code)

Max Activating Token Index: 522

Text #1

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3314. Min Act: -0.0003

Data Index: 1390882 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3238. Min Act: -0.0003

Data Index: 1649211 (Python Code)

Max Activating Token Index: 210

Text #3

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3304. Min Act: -0.0003

Data Index: 1385020 (Python Code)

Max Activating Token Index: 879

Text #4

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3293. Min Act: -0.0003

Data Index: 1593357 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3025. Min Act: -0.0003

Data Index: 1597570 (Python Code)

Max Activating Token Index: 524

Text #6

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3121. Min Act: -0.0003

Data Index: 1480188 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3098. Min Act: -0.0003

Data Index: 1520885 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.2987. Min Act: -0.0003

Data Index: 1586267 (Python Code)

Max Activating Token Index: 448

Text #9

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3095. Min Act: -0.0003

Data Index: 1475736 (Python Code)

Max Activating Token Index: 864

Text #10

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3075. Min Act: -0.0003

Data Index: 1578323 (Python Code)

Max Activating Token Index: 430

Text #11

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3075. Min Act: -0.0003

Data Index: 1553472 (Python Code)

Max Activating Token Index: 86

Text #12

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3077. Min Act: -0.0003

Data Index: 1368205 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.2857. Min Act: -0.0003

Data Index: 1563955 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3136. Min Act: -0.0003

Data Index: 1649528 (Python Code)

Max Activating Token Index: 608

Text #15

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3037. Min Act: -0.0003

Data Index: 1579518 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.2933. Min Act: -0.0003

Data Index: 1541407 (Python Code)

Max Activating Token Index: 487

Text #17

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.3028. Min Act: -0.0003

Data Index: 1614480 (Python Code)

Max Activating Token Index: 967

Text #18

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.2907. Min Act: -0.0003

Data Index: 1441824 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 0.3577. Min Range: -0.3577

Max Act: 0.2991. Min Act: -0.0003

Data Index: 1649556 (Python Code)

Max Activating Token Index: 328