Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1364 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1188928 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2386. Min Act: -0.0000

Data Index: 213795 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2268. Min Act: 0.0000

Data Index: 62167 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2318. Min Act: -0.0000

Data Index: 978912 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2271. Min Act: -0.0000

Data Index: 749211 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2235. Min Act: 0.0000

Data Index: 774818 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2114. Min Act: -0.0001

Data Index: 897885 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2163. Min Act: 0.0000

Data Index: 33017 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2077. Min Act: -0.0000

Data Index: 206857 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2129. Min Act: -0.0001

Data Index: 798265 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2059. Min Act: -0.0000

Data Index: 198051 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2037. Min Act: -0.0001

Data Index: 508452 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1136914 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.1996. Min Act: -0.0000

Data Index: 966893 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.1986. Min Act: -0.0001

Data Index: 118021 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.1951. Min Act: -0.0000

Data Index: 399450 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1116220 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.1901. Min Act: -0.0000

Data Index: 912270 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.1910. Min Act: -0.0000

Data Index: 5139 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.1833. Min Act: -0.0000

Data Index: 918051 (C4 (Web Text))

Max Activating Token Index: 366