Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4481 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.9921. Min Act: -0.0000

Data Index: 1180643 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.8045. Min Act: -0.0000

Data Index: 1117664 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.5272. Min Act: -0.0000

Data Index: 1131178 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.2530. Min Act: -0.0000

Data Index: 52144 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.3669. Min Act: -0.0000

Data Index: 1310931 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.3334. Min Act: -0.0000

Data Index: 1435344 (Python Code)

Max Activating Token Index: 93

Text #6

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.1964. Min Act: -0.0000

Data Index: 1313797 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.2798. Min Act: -0.0000

Data Index: 280110 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.2817. Min Act: -0.0000

Data Index: 463625 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.2115. Min Act: -0.0000

Data Index: 202937 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1340581 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1443486 (Python Code)

Max Activating Token Index: 855

Text #12

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.2315. Min Act: -0.0000

Data Index: 759893 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.2622. Min Act: -0.0000

Data Index: 1477937 (Python Code)

Max Activating Token Index: 956

Text #14

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.3186. Min Act: -0.0000

Data Index: 126697 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1330636 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.1037. Min Act: -0.0000

Data Index: 310523 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1027205 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1070001 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.9921. Min Range: -1.9921

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1595122 (Python Code)

Max Activating Token Index: 91