Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 752 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1279554 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1234. Min Act: -0.0002

Data Index: 864025 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1075966 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1090. Min Act: -0.0002

Data Index: 137200 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1055. Min Act: -0.0002

Data Index: 483011 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1220630 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0949. Min Act: -0.0002

Data Index: 1302109 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0976. Min Act: -0.0002

Data Index: 434146 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0947. Min Act: -0.0002

Data Index: 429510 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1618261 (Python Code)

Max Activating Token Index: 585

Text #10

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0946. Min Act: -0.0002

Data Index: 556828 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0942. Min Act: -0.0002

Data Index: 619933 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0900. Min Act: -0.0002

Data Index: 55121 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1108863 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0888. Min Act: -0.0002

Data Index: 219249 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0891. Min Act: -0.0002

Data Index: 530832 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0866. Min Act: -0.0002

Data Index: 911192 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0863. Min Act: -0.0002

Data Index: 121687 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0860. Min Act: -0.0002

Data Index: 791136 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0862. Min Act: -0.0002

Data Index: 14704 (C4 (Web Text))

Max Activating Token Index: 294