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

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

Neuron 2066 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.7072. Min Act: -0.0000

Data Index: 367664 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.4787. Min Act: -0.0000

Data Index: 603614 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.3556. Min Act: -0.0000

Data Index: 28796 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.2082. Min Act: -0.0000

Data Index: 1561143 (Python Code)

Max Activating Token Index: 512

Text #4

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.1300. Min Act: -0.0000

Data Index: 187184 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.2535. Min Act: -0.0000

Data Index: 515832 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.2278. Min Act: -0.0000

Data Index: 151298 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.2144. Min Act: -0.0000

Data Index: 1129107 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.2096. Min Act: -0.0000

Data Index: 316287 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.1947. Min Act: -0.0000

Data Index: 1399066 (Python Code)

Max Activating Token Index: 530

Text #10

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.1467. Min Act: -0.0000

Data Index: 228572 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.1839. Min Act: -0.0000

Data Index: 1474731 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.0476. Min Act: -0.0000

Data Index: 1597547 (Python Code)

Max Activating Token Index: 142

Text #13

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.0346. Min Act: -0.0000

Data Index: 1412010 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.0579. Min Act: -0.0000

Data Index: 1274869 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.0961. Min Act: -0.0000

Data Index: 1480046 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.0092. Min Act: -0.0000

Data Index: 75679 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.9971. Min Act: -0.0000

Data Index: 1488796 (Python Code)

Max Activating Token Index: 545

Text #18

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.9914. Min Act: -0.0000

Data Index: 949209 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.9375. Min Act: -0.0000

Data Index: 409899 (C4 (Web Text))

Max Activating Token Index: 573