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

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

Neuron 3819 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1279765 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2261. Min Act: -0.0000

Data Index: 127151 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2482. Min Act: -0.0000

Data Index: 117148 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1059852 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2400. Min Act: -0.0000

Data Index: 101016 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2181. Min Act: -0.0000

Data Index: 272850 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1990. Min Act: -0.0000

Data Index: 841729 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2101. Min Act: -0.0001

Data Index: 867650 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1043344 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1995. Min Act: -0.0001

Data Index: 260603 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2019. Min Act: -0.0001

Data Index: 1184129 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1148624 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2101. Min Act: -0.0000

Data Index: 936775 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1921. Min Act: -0.0000

Data Index: 16669 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2081. Min Act: -0.0001

Data Index: 666045 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1987. Min Act: -0.0000

Data Index: 975414 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1198878 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1060470 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1873. Min Act: -0.0000

Data Index: 233448 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1948. Min Act: -0.0001

Data Index: 604867 (C4 (Web Text))

Max Activating Token Index: 517