Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4704 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.6152. Min Act: -0.0000

Data Index: 773940 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1222716 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.7798. Min Act: -0.0000

Data Index: 185554 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.7897. Min Act: -0.0000

Data Index: 230066 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.6755. Min Act: -0.0000

Data Index: 306928 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.7019. Min Act: -0.0000

Data Index: 5743 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.7196. Min Act: -0.0000

Data Index: 868718 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.7089. Min Act: -0.0000

Data Index: 419643 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1082807 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.5942. Min Act: -0.0000

Data Index: 992335 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.5777. Min Act: -0.0000

Data Index: 996955 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.5779. Min Act: -0.0000

Data Index: 210187 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.5222. Min Act: -0.0000

Data Index: 459615 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1052768 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.4992. Min Act: -0.0000

Data Index: 516107 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1214600 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.4629. Min Act: -0.0000

Data Index: 954705 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.5044. Min Act: -0.0000

Data Index: 718676 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1313739 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.6152. Min Range: -1.6152

Max Act: 0.4550. Min Act: -0.0000

Data Index: 297346 (C4 (Web Text))

Max Activating Token Index: 990