Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 88 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1182. Min Act: -0.0001

Data Index: 804983 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1164. Min Act: -0.0001

Data Index: 77456 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1053. Min Act: -0.0001

Data Index: 995951 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1202980 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1059. Min Act: -0.0001

Data Index: 314343 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1228213 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1138171 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0981. Min Act: -0.0001

Data Index: 539948 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1228130 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0968. Min Act: -0.0001

Data Index: 142713 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0905. Min Act: -0.0001

Data Index: 685218 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0943. Min Act: -0.0001

Data Index: 734643 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0963. Min Act: -0.0001

Data Index: 336007 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1085155 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1197676 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0943. Min Act: -0.0001

Data Index: 986323 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0909. Min Act: -0.0001

Data Index: 544250 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0863. Min Act: -0.0001

Data Index: 759307 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0896. Min Act: -0.0001

Data Index: 344669 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0864. Min Act: -0.0001

Data Index: 3872 (C4 (Web Text))

Max Activating Token Index: 900