Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 391 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.8029. Min Act: -0.0001

Data Index: 1220745 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4882. Min Act: -0.0001

Data Index: 447874 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4189. Min Act: -0.0001

Data Index: 779183 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4534. Min Act: -0.0001

Data Index: 1217426 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.7000. Min Act: -0.0000

Data Index: 978639 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.8138. Min Act: -0.0001

Data Index: 927135 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.6775. Min Act: -0.0001

Data Index: 118471 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.7063. Min Act: -0.0000

Data Index: 318939 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.5421. Min Act: -0.0001

Data Index: 996974 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.8040. Min Act: -0.0000

Data Index: 371579 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.9404. Min Act: -0.0000

Data Index: 125420 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.7531. Min Act: -0.0001

Data Index: 531766 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.6732. Min Act: -0.0001

Data Index: 168986 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.2077. Min Act: -0.0001

Data Index: 646467 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.5108. Min Act: -0.0001

Data Index: 1101359 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.5004. Min Act: -0.0001

Data Index: 1037224 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.3234. Min Act: -0.0001

Data Index: 178044 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.2835. Min Act: -0.0000

Data Index: 1356577 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.3060. Min Act: -0.0001

Data Index: 840456 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 4.8029. Min Range: -4.8029

Max Act: 3.4079. Min Act: -0.0001

Data Index: 240304 (C4 (Web Text))

Max Activating Token Index: 349