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

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

Neuron 102 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4868. Min Act: -0.0001

Data Index: 665887 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4924. Min Act: -0.0001

Data Index: 1340960 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.5086. Min Act: -0.0001

Data Index: 445055 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4612. Min Act: -0.0001

Data Index: 211176 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4773. Min Act: -0.0001

Data Index: 658920 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4785. Min Act: -0.0001

Data Index: 154272 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4280. Min Act: -0.0001

Data Index: 1084706 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4449. Min Act: -0.0001

Data Index: 226929 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4452. Min Act: -0.0001

Data Index: 708878 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4318. Min Act: -0.0001

Data Index: 759208 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4549. Min Act: -0.0001

Data Index: 919375 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4277. Min Act: -0.0001

Data Index: 67350 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4135. Min Act: -0.0001

Data Index: 1345022 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4196. Min Act: -0.0001

Data Index: 871595 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4311. Min Act: -0.0001

Data Index: 972038 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4083. Min Act: -0.0001

Data Index: 962091 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4085. Min Act: -0.0001

Data Index: 1023868 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4220. Min Act: -0.0001

Data Index: 528986 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4268. Min Act: -0.0001

Data Index: 1069146 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4275. Min Act: -0.0001

Data Index: 167333 (C4 (Web Text))

Max Activating Token Index: 858