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

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

Neuron 5817 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.7649. Min Act: -0.0000

Data Index: 1223109 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.7577. Min Act: -0.0000

Data Index: 845198 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.2905. Min Act: -0.0000

Data Index: 419099 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.2910. Min Act: -0.0000

Data Index: 529144 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.2546. Min Act: -0.0000

Data Index: 645545 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.3041. Min Act: -0.0000

Data Index: 871889 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1593284 (Python Code)

Max Activating Token Index: 293

Text #7

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.0478. Min Act: -0.0000

Data Index: 82817 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.0694. Min Act: -0.0000

Data Index: 71384 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.0246. Min Act: -0.0000

Data Index: 520136 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 1.7649. Min Range: -1.7649

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1003948 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.0244. Min Act: -0.0000

Data Index: 297719 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.7649. Min Range: -1.7649

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1227015 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.0360. Min Act: -0.0000

Data Index: 529244 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 1.7649. Min Range: -1.7649

Max Act: 0.9254. Min Act: -0.0000

Data Index: 573394 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1389742 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 1.7649. Min Range: -1.7649

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1567697 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 1.7649. Min Range: -1.7649

Max Act: 0.9355. Min Act: -0.0000

Data Index: 938046 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.7649. Min Range: -1.7649

Max Act: 1.0201. Min Act: -0.0000

Data Index: 265196 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 1.7649. Min Range: -1.7649

Max Act: 0.9508. Min Act: -0.0000

Data Index: 756320 (C4 (Web Text))

Max Activating Token Index: 622