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

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

Neuron 83 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.8367. Min Act: -0.0001

Data Index: 1017310 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7252. Min Act: -0.0001

Data Index: 847702 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7376. Min Act: -0.0000

Data Index: 276659 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7071. Min Act: -0.0001

Data Index: 1215176 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6749. Min Act: -0.0001

Data Index: 535426 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6516. Min Act: -0.0001

Data Index: 1239934 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6942. Min Act: -0.0001

Data Index: 585691 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7036. Min Act: -0.0001

Data Index: 1120489 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6504. Min Act: -0.0001

Data Index: 1190079 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6853. Min Act: -0.0001

Data Index: 708928 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6219. Min Act: -0.0000

Data Index: 357207 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6216. Min Act: -0.0001

Data Index: 430894 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1111588 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6083. Min Act: -0.0001

Data Index: 1327991 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6177. Min Act: -0.0001

Data Index: 1282061 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6075. Min Act: -0.0001

Data Index: 934545 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1129651 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6075. Min Act: -0.0001

Data Index: 979150 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5935. Min Act: -0.0001

Data Index: 98849 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5954. Min Act: -0.0001

Data Index: 995009 (C4 (Web Text))

Max Activating Token Index: 337