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

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

Neuron 1748 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: 0.3678. Min Range: -0.3678

Max Act: 0.3678. Min Act: -0.0001

Data Index: 9057 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.3346. Min Act: -0.0001

Data Index: 553865 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.3281. Min Act: -0.0001

Data Index: 823188 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.3240. Min Act: -0.0001

Data Index: 718946 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.3134. Min Act: -0.0001

Data Index: 1062416 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.3189. Min Act: -0.0001

Data Index: 385116 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.3066. Min Act: -0.0001

Data Index: 1160499 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.3103. Min Act: -0.0001

Data Index: 1053875 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.2994. Min Act: -0.0001

Data Index: 918542 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.3103. Min Act: -0.0001

Data Index: 635485 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1180459 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.2965. Min Act: -0.0001

Data Index: 965312 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.2848. Min Act: -0.0001

Data Index: 325188 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.2823. Min Act: -0.0001

Data Index: 517030 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.2791. Min Act: -0.0001

Data Index: 965003 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.2906. Min Act: -0.0001

Data Index: 976131 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.2948. Min Act: -0.0001

Data Index: 1191785 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.2948. Min Act: -0.0001

Data Index: 953425 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.2935. Min Act: -0.0001

Data Index: 216089 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.3678. Min Range: -0.3678

Max Act: 0.2921. Min Act: -0.0001

Data Index: 1342809 (C4 (Web Text))

Max Activating Token Index: 824