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

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

Neuron 5514 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: 2.4647. Min Range: -2.4647

Max Act: 2.4647. Min Act: -0.0000

Data Index: 135930 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 2.4647. Min Range: -2.4647

Max Act: 2.0471. Min Act: -0.0000

Data Index: 40387 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 2.4647. Min Range: -2.4647

Max Act: 2.0339. Min Act: -0.0000

Data Index: 531380 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.8359. Min Act: -0.0000

Data Index: 988573 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.7179. Min Act: -0.0000

Data Index: 1331019 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.7795. Min Act: -0.0000

Data Index: 1341288 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.6819. Min Act: -0.0000

Data Index: 700586 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.8479. Min Act: -0.0000

Data Index: 807462 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.6070. Min Act: -0.0000

Data Index: 975830 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.7008. Min Act: -0.0000

Data Index: 1008920 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.6840. Min Act: -0.0000

Data Index: 1043960 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.6799. Min Act: -0.0000

Data Index: 478315 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.7404. Min Act: -0.0000

Data Index: 711858 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.6405. Min Act: -0.0000

Data Index: 984447 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.5444. Min Act: -0.0000

Data Index: 1013771 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.5229. Min Act: -0.0000

Data Index: 345192 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.6112. Min Act: -0.0000

Data Index: 101771 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.4977. Min Act: -0.0000

Data Index: 733359 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.4095. Min Act: -0.0000

Data Index: 896356 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 2.4647. Min Range: -2.4647

Max Act: 1.6724. Min Act: -0.0000

Data Index: 1322930 (C4 (Web Text))

Max Activating Token Index: 119