Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1434 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1168. Min Act: -0.0006

Data Index: 61472 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1035. Min Act: -0.0006

Data Index: 20325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0968. Min Act: -0.0005

Data Index: 580283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0943. Min Act: -0.0005

Data Index: 1455998 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0928. Min Act: -0.0006

Data Index: 594192 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0907. Min Act: -0.0006

Data Index: 82366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0914. Min Act: -0.0006

Data Index: 1167256 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0888. Min Act: -0.0006

Data Index: 488244 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0858. Min Act: -0.0006

Data Index: 1114178 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0872. Min Act: -0.0006

Data Index: 844187 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0840. Min Act: -0.0005

Data Index: 453029 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0864. Min Act: -0.0005

Data Index: 701218 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0843. Min Act: -0.0006

Data Index: 128964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0840. Min Act: -0.0006

Data Index: 629332 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0837. Min Act: -0.0005

Data Index: 958504 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0812. Min Act: -0.0006

Data Index: 51128 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0827. Min Act: -0.0006

Data Index: 379257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0799. Min Act: -0.0006

Data Index: 815613 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0808. Min Act: -0.0005

Data Index: 317597 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0789. Min Act: -0.0006

Data Index: 217951 (C4 (Web Text))

Max Activating Token Index: 1023