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

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

Neuron 3667 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6746. Min Range: -4.6746

Max Act: 4.6746. Min Act: -0.0000

Data Index: 1432327 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 4.6746. Min Range: -4.6746

Max Act: 4.6190. Min Act: -0.0000

Data Index: 1380129 (Python Code)

Max Activating Token Index: 985

Text #2

Max Range: 4.6746. Min Range: -4.6746

Max Act: 4.4272. Min Act: -0.0000

Data Index: 1368562 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 4.6746. Min Range: -4.6746

Max Act: 4.0547. Min Act: 0.0000

Data Index: 1430274 (Python Code)

Max Activating Token Index: 126

Text #4

Max Range: 4.6746. Min Range: -4.6746

Max Act: 3.4427. Min Act: 0.0000

Data Index: 1463448 (Python Code)

Max Activating Token Index: 454

Text #5

Max Range: 4.6746. Min Range: -4.6746

Max Act: 3.0415. Min Act: 0.0000

Data Index: 1536238 (Python Code)

Max Activating Token Index: 327

Text #6

Max Range: 4.6746. Min Range: -4.6746

Max Act: 3.0882. Min Act: 0.0000

Data Index: 1445718 (Python Code)

Max Activating Token Index: 991

Text #7

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.7937. Min Act: 0.0000

Data Index: 1432777 (Python Code)

Max Activating Token Index: 262

Text #8

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.6771. Min Act: -0.0000

Data Index: 1513208 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.7894. Min Act: -0.0000

Data Index: 1645176 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.5066. Min Act: 0.0000

Data Index: 1602051 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.4943. Min Act: -0.0000

Data Index: 1641288 (Python Code)

Max Activating Token Index: 438

Text #12

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.5820. Min Act: 0.0000

Data Index: 1583882 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.5068. Min Act: -0.0000

Data Index: 1541989 (Python Code)

Max Activating Token Index: 864

Text #14

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.5879. Min Act: -0.0000

Data Index: 1555026 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.1801. Min Act: -0.0000

Data Index: 1482881 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.1982. Min Act: 0.0000

Data Index: 1613309 (Python Code)

Max Activating Token Index: 186

Text #17

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.3972. Min Act: -0.0000

Data Index: 1499965 (Python Code)

Max Activating Token Index: 1005

Text #18

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.2735. Min Act: -0.0000

Data Index: 1433885 (Python Code)

Max Activating Token Index: 535

Text #19

Max Range: 4.6746. Min Range: -4.6746

Max Act: 2.3031. Min Act: -0.0000

Data Index: 833184 (C4 (Web Text))

Max Activating Token Index: 965