Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 92 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8325. Min Act: -0.0001

Data Index: 64736 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7354. Min Act: -0.0001

Data Index: 483823 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7376. Min Act: -0.0001

Data Index: 771698 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6577. Min Act: -0.0001

Data Index: 734374 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7412. Min Act: -0.0001

Data Index: 622639 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7109. Min Act: -0.0001

Data Index: 364173 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7286. Min Act: -0.0001

Data Index: 1268399 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6831. Min Act: -0.0001

Data Index: 377541 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7014. Min Act: -0.0001

Data Index: 897921 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7007. Min Act: -0.0001

Data Index: 1110671 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7227. Min Act: -0.0001

Data Index: 1234916 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6405. Min Act: -0.0001

Data Index: 1079206 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6727. Min Act: -0.0001

Data Index: 329220 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6900. Min Act: -0.0001

Data Index: 970256 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6685. Min Act: -0.0001

Data Index: 631422 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6854. Min Act: -0.0001

Data Index: 303128 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6611. Min Act: -0.0001

Data Index: 135561 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6657. Min Act: -0.0001

Data Index: 1327722 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6633. Min Act: -0.0001

Data Index: 225449 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6793. Min Act: -0.0001

Data Index: 1325110 (C4 (Web Text))

Max Activating Token Index: 612