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

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

Neuron 3653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.8415. Min Act: -0.0000

Data Index: 1254625 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.7566. Min Act: -0.0000

Data Index: 771896 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.6636. Min Act: -0.0000

Data Index: 216320 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.5539. Min Act: -0.0000

Data Index: 1143365 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.6269. Min Act: -0.0000

Data Index: 45153 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.5821. Min Act: -0.0000

Data Index: 168803 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.5306. Min Act: -0.0000

Data Index: 498229 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.5016. Min Act: -0.0000

Data Index: 475205 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.4065. Min Act: -0.0000

Data Index: 724160 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.4305. Min Act: -0.0000

Data Index: 378702 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.4967. Min Act: -0.0000

Data Index: 819087 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.3679. Min Act: -0.0000

Data Index: 1066956 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.3893. Min Act: -0.0000

Data Index: 1096500 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.3745. Min Act: -0.0000

Data Index: 690585 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.3651. Min Act: -0.0000

Data Index: 1032062 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.3265. Min Act: -0.0000

Data Index: 970765 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.3857. Min Act: -0.0000

Data Index: 975278 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.3908. Min Act: -0.0000

Data Index: 962803 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.4054. Min Act: -0.0000

Data Index: 1313913 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.8415. Min Range: -1.8415

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1117044 (C4 (Web Text))

Max Activating Token Index: 35