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

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

Neuron 316 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3570. Min Act: -0.0001

Data Index: 920965 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3081. Min Act: -0.0001

Data Index: 869874 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3310. Min Act: -0.0001

Data Index: 927414 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3115. Min Act: -0.0001

Data Index: 683558 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3109. Min Act: -0.0001

Data Index: 1336174 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2980. Min Act: -0.0001

Data Index: 32990 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1305273 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3066. Min Act: -0.0001

Data Index: 509234 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3117. Min Act: -0.0001

Data Index: 16086 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3007. Min Act: -0.0001

Data Index: 974908 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2910. Min Act: -0.0001

Data Index: 1156399 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2985. Min Act: -0.0001

Data Index: 428001 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2849. Min Act: -0.0001

Data Index: 1056824 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2962. Min Act: -0.0001

Data Index: 563116 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2826. Min Act: -0.0001

Data Index: 595388 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2909. Min Act: -0.0000

Data Index: 510302 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2864. Min Act: -0.0001

Data Index: 463982 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1081641 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2900. Min Act: -0.0001

Data Index: 422744 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2684. Min Act: -0.0000

Data Index: 41329 (C4 (Web Text))

Max Activating Token Index: 27