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

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

Neuron 481 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5096. Min Range: -2.5096

Max Act: 2.5096. Min Act: -0.0000

Data Index: 389632 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 2.5096. Min Range: -2.5096

Max Act: 2.3882. Min Act: -0.0000

Data Index: 794825 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 2.5096. Min Range: -2.5096

Max Act: 2.0937. Min Act: -0.0000

Data Index: 916053 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.8990. Min Act: -0.0000

Data Index: 480985 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.7810. Min Act: -0.0000

Data Index: 602771 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.7759. Min Act: -0.0000

Data Index: 834928 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.8735. Min Act: -0.0000

Data Index: 793307 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.8420. Min Act: -0.0000

Data Index: 151696 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.7430. Min Act: -0.0000

Data Index: 214040 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.6472. Min Act: -0.0000

Data Index: 31870 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.7167. Min Act: -0.0000

Data Index: 668082 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.6490. Min Act: -0.0000

Data Index: 1116264 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.7226. Min Act: -0.0000

Data Index: 382801 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.7002. Min Act: -0.0000

Data Index: 809875 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.6775. Min Act: -0.0000

Data Index: 392531 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.5701. Min Act: -0.0000

Data Index: 30962 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.8618. Min Act: -0.0000

Data Index: 309502 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.6369. Min Act: -0.0000

Data Index: 513161 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.6228. Min Act: -0.0000

Data Index: 759982 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 2.5096. Min Range: -2.5096

Max Act: 1.5537. Min Act: -0.0000

Data Index: 707772 (C4 (Web Text))

Max Activating Token Index: 515