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

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

Neuron 1178 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3662. Min Range: -2.3662

Max Act: 2.3662. Min Act: -0.0000

Data Index: 1155881 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 2.3662. Min Range: -2.3662

Max Act: 2.3446. Min Act: -0.0000

Data Index: 732659 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 2.3662. Min Range: -2.3662

Max Act: 2.3195. Min Act: -0.0000

Data Index: 908921 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 2.3662. Min Range: -2.3662

Max Act: 2.1301. Min Act: -0.0000

Data Index: 228045 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 2.3662. Min Range: -2.3662

Max Act: 2.0852. Min Act: -0.0000

Data Index: 838768 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.9337. Min Act: -0.0000

Data Index: 545088 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.9054. Min Act: -0.0000

Data Index: 24028 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.8943. Min Act: -0.0000

Data Index: 547570 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.9026. Min Act: -0.0000

Data Index: 1175666 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.7728. Min Act: -0.0000

Data Index: 572920 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 2.3662. Min Range: -2.3662

Max Act: 2.0820. Min Act: -0.0000

Data Index: 748673 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.8690. Min Act: -0.0000

Data Index: 1100815 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.9187. Min Act: -0.0000

Data Index: 632039 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.8945. Min Act: -0.0000

Data Index: 928580 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.7569. Min Act: -0.0000

Data Index: 285921 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.7477. Min Act: -0.0000

Data Index: 819400 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.6874. Min Act: -0.0000

Data Index: 908652 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.6921. Min Act: -0.0000

Data Index: 1300848 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.6865. Min Act: -0.0000

Data Index: 1150918 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 2.3662. Min Range: -2.3662

Max Act: 1.6798. Min Act: -0.0000

Data Index: 1094757 (C4 (Web Text))

Max Activating Token Index: 342