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

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

Neuron 4477 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: 1.1529. Min Range: -1.1529

Max Act: 1.1529. Min Act: -0.0000

Data Index: 154531 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1107957 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.8978. Min Act: -0.0000

Data Index: 475720 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.8272. Min Act: -0.0000

Data Index: 766770 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7955. Min Act: -0.0000

Data Index: 609501 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1011781 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7440. Min Act: -0.0000

Data Index: 658430 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7352. Min Act: -0.0000

Data Index: 501164 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7518. Min Act: -0.0000

Data Index: 755876 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7397. Min Act: -0.0000

Data Index: 869601 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7886. Min Act: -0.0000

Data Index: 505404 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7889. Min Act: -0.0000

Data Index: 84918 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1223682 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7468. Min Act: -0.0000

Data Index: 1095022 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7047. Min Act: -0.0000

Data Index: 932305 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7117. Min Act: -0.0000

Data Index: 497149 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.6865. Min Act: -0.0000

Data Index: 172473 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1518636 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.6779. Min Act: -0.0000

Data Index: 716390 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.6846. Min Act: -0.0000

Data Index: 576217 (C4 (Web Text))

Max Activating Token Index: 242