Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3141 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2569. Min Range: -1.2569

Max Act: 1.2569. Min Act: -0.0000

Data Index: 858666 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 1.2569. Min Range: -1.2569

Max Act: 1.2275. Min Act: -0.0000

Data Index: 862072 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 1.2569. Min Range: -1.2569

Max Act: 1.2294. Min Act: -0.0000

Data Index: 815638 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 1.2569. Min Range: -1.2569

Max Act: 1.0204. Min Act: -0.0000

Data Index: 517380 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.2569. Min Range: -1.2569

Max Act: 1.0841. Min Act: -0.0000

Data Index: 18484 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.2569. Min Range: -1.2569

Max Act: 1.0338. Min Act: -0.0000

Data Index: 27735 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.9990. Min Act: -0.0000

Data Index: 851414 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.9703. Min Act: -0.0000

Data Index: 614230 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.9314. Min Act: -0.0000

Data Index: 962456 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1058574 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.9397. Min Act: -0.0000

Data Index: 484777 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.9422. Min Act: -0.0000

Data Index: 937742 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.8847. Min Act: -0.0000

Data Index: 476040 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1045512 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1320338 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.9247. Min Act: -0.0000

Data Index: 657206 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.8732. Min Act: -0.0000

Data Index: 508290 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.8122. Min Act: -0.0000

Data Index: 120039 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.8481. Min Act: -0.0000

Data Index: 174934 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 1.2569. Min Range: -1.2569

Max Act: 0.7898. Min Act: -0.0000

Data Index: 917626 (C4 (Web Text))

Max Activating Token Index: 848