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

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

Neuron 5923 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1265. Min Range: -1.1265

Max Act: 1.1265. Min Act: -0.0000

Data Index: 814942 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1321346 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.9383. Min Act: -0.0000

Data Index: 558290 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1067675 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1145986 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1115984 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.9010. Min Act: -0.0000

Data Index: 306689 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.8618. Min Act: -0.0000

Data Index: 597114 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1110465 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.8697. Min Act: -0.0000

Data Index: 103447 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.8504. Min Act: -0.0000

Data Index: 960888 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.7817. Min Act: -0.0000

Data Index: 368788 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.8300. Min Act: -0.0000

Data Index: 862549 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.7534. Min Act: -0.0000

Data Index: 919269 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1044001 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.7962. Min Act: -0.0000

Data Index: 713559 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.7752. Min Act: -0.0000

Data Index: 897532 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.7061. Min Act: -0.0000

Data Index: 605898 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.7489. Min Act: -0.0000

Data Index: 646270 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.1265. Min Range: -1.1265

Max Act: 0.7758. Min Act: -0.0000

Data Index: 720619 (C4 (Web Text))

Max Activating Token Index: 607