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

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

Neuron 3428 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.6492. Min Act: -0.0002

Data Index: 1209669 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.6535. Min Act: -0.0002

Data Index: 1236857 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.6070. Min Act: -0.0002

Data Index: 1168416 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5851. Min Act: -0.0002

Data Index: 765957 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.6071. Min Act: -0.0002

Data Index: 645948 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5920. Min Act: -0.0002

Data Index: 272632 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5610. Min Act: -0.0002

Data Index: 522046 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5524. Min Act: -0.0002

Data Index: 1213827 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5832. Min Act: -0.0002

Data Index: 84019 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5502. Min Act: -0.0002

Data Index: 466283 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5290. Min Act: -0.0002

Data Index: 5441 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5478. Min Act: -0.0002

Data Index: 477383 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5882. Min Act: -0.0002

Data Index: 527721 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5620. Min Act: -0.0002

Data Index: 1289575 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5323. Min Act: -0.0002

Data Index: 777584 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5658. Min Act: -0.0002

Data Index: 1162987 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5234. Min Act: -0.0002

Data Index: 39944 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5726. Min Act: -0.0002

Data Index: 347255 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5436. Min Act: -0.0002

Data Index: 142028 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5454. Min Act: -0.0002

Data Index: 889693 (C4 (Web Text))

Max Activating Token Index: 415