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

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

Neuron 2300 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3896. Min Range: -2.3896

Max Act: 2.3896. Min Act: -0.0000

Data Index: 735872 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 2.3896. Min Range: -2.3896

Max Act: 2.3160. Min Act: -0.0000

Data Index: 993723 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 2.3896. Min Range: -2.3896

Max Act: 2.1560. Min Act: -0.0000

Data Index: 914846 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 2.3896. Min Range: -2.3896

Max Act: 2.2077. Min Act: -0.0000

Data Index: 332849 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 2.3896. Min Range: -2.3896

Max Act: 2.0650. Min Act: -0.0000

Data Index: 747121 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 2.3896. Min Range: -2.3896

Max Act: 2.1458. Min Act: -0.0000

Data Index: 420312 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 2.3896. Min Range: -2.3896

Max Act: 2.1419. Min Act: -0.0000

Data Index: 683706 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.9742. Min Act: -0.0000

Data Index: 216199 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.8291. Min Act: -0.0000

Data Index: 979618 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.9171. Min Act: -0.0000

Data Index: 1218215 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.7933. Min Act: -0.0000

Data Index: 127538 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.8957. Min Act: -0.0000

Data Index: 97418 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.7381. Min Act: -0.0000

Data Index: 216468 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.7967. Min Act: -0.0000

Data Index: 543440 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.7753. Min Act: -0.0000

Data Index: 1168977 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.7611. Min Act: -0.0000

Data Index: 54379 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.7432. Min Act: -0.0000

Data Index: 263620 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.7976. Min Act: -0.0000

Data Index: 1165920 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.4455. Min Act: -0.0000

Data Index: 285710 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 2.3896. Min Range: -2.3896

Max Act: 1.6953. Min Act: -0.0000

Data Index: 438505 (C4 (Web Text))

Max Activating Token Index: 959