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

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

Neuron 3278 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6678. Min Act: -0.0001

Data Index: 120837 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6157. Min Act: -0.0001

Data Index: 905863 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6371. Min Act: -0.0001

Data Index: 779901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6102. Min Act: -0.0001

Data Index: 749326 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6105. Min Act: -0.0000

Data Index: 582299 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6094. Min Act: -0.0001

Data Index: 263836 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6059. Min Act: -0.0000

Data Index: 292022 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1312951 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5813. Min Act: -0.0001

Data Index: 881379 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6136. Min Act: -0.0001

Data Index: 513148 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5871. Min Act: -0.0001

Data Index: 362254 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6114. Min Act: -0.0001

Data Index: 101529 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6040. Min Act: -0.0000

Data Index: 635158 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5875. Min Act: -0.0000

Data Index: 48511 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1332693 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6262. Min Act: -0.0001

Data Index: 215787 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6199. Min Act: -0.0000

Data Index: 66447 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1082614 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5958. Min Act: -0.0001

Data Index: 425009 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5747. Min Act: -0.0001

Data Index: 767696 (C4 (Web Text))

Max Activating Token Index: 16