Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 22 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2593. Min Act: -0.0004

Data Index: 772519 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2350. Min Act: -0.0004

Data Index: 454994 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2390. Min Act: -0.0004

Data Index: 1280866 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2346. Min Act: -0.0004

Data Index: 1164636 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2204. Min Act: -0.0004

Data Index: 486516 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2184. Min Act: -0.0004

Data Index: 131872 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2111. Min Act: -0.0004

Data Index: 270258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.1990. Min Act: -0.0004

Data Index: 215523 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2055. Min Act: -0.0004

Data Index: 278578 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2052. Min Act: -0.0004

Data Index: 1203015 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2051. Min Act: -0.0004

Data Index: 1009754 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2049. Min Act: -0.0004

Data Index: 53603 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2044. Min Act: -0.0004

Data Index: 746607 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.2041. Min Act: -0.0004

Data Index: 503248 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.1926. Min Act: -0.0004

Data Index: 1275385 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.1983. Min Act: -0.0004

Data Index: 1077674 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.1980. Min Act: -0.0004

Data Index: 329454 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.1953. Min Act: -0.0004

Data Index: 685280 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.1911. Min Act: -0.0004

Data Index: 141027 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.2593. Min Range: -0.2593

Max Act: 0.1952. Min Act: -0.0004

Data Index: 1153255 (C4 (Web Text))

Max Activating Token Index: 1023