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

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

Neuron 3019 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0694. Min Range: -1.0694

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1244458 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.9582. Min Act: -0.0000

Data Index: 2014 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.9099. Min Act: -0.0000

Data Index: 220858 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.9194. Min Act: -0.0000

Data Index: 533249 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8897. Min Act: -0.0000

Data Index: 926909 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1221849 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1272743 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8256. Min Act: -0.0000

Data Index: 289567 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.9255. Min Act: -0.0000

Data Index: 107200 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8239. Min Act: -0.0000

Data Index: 560313 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1308143 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8630. Min Act: -0.0000

Data Index: 356459 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1336662 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7600. Min Act: -0.0000

Data Index: 349944 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7994. Min Act: -0.0000

Data Index: 758563 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7471. Min Act: -0.0000

Data Index: 799931 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1010372 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7880. Min Act: -0.0000

Data Index: 486965 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7728. Min Act: -0.0000

Data Index: 705823 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.0694. Min Range: -1.0694

Max Act: 0.7935. Min Act: -0.0000

Data Index: 97622 (C4 (Web Text))

Max Activating Token Index: 433