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

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

Neuron 3633 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.4496. Min Act: 0.0000

Data Index: 677052 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.4031. Min Act: -0.0000

Data Index: 261751 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3340. Min Act: -0.0000

Data Index: 987581 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3284. Min Act: -0.0000

Data Index: 941930 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3109. Min Act: -0.0000

Data Index: 51611 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3102. Min Act: -0.0000

Data Index: 578225 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3107. Min Act: 0.0000

Data Index: 647729 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1307587 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3204. Min Act: 0.0000

Data Index: 1250878 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3064. Min Act: 0.0000

Data Index: 428716 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2782. Min Act: -0.0000

Data Index: 17936 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2857. Min Act: -0.0000

Data Index: 44802 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2776. Min Act: 0.0000

Data Index: 456043 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2846. Min Act: -0.0000

Data Index: 23904 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2832. Min Act: 0.0000

Data Index: 546698 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2820. Min Act: -0.0000

Data Index: 680353 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1351485 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2748. Min Act: -0.0000

Data Index: 683970 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2807. Min Act: -0.0000

Data Index: 532420 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1279402 (C4 (Web Text))

Max Activating Token Index: 964