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

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

Neuron 4068 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: 7.0368. Min Range: -7.0368

Max Act: 7.0368. Min Act: -0.0000

Data Index: 204825 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 7.0368. Min Range: -7.0368

Max Act: 6.4075. Min Act: -0.0000

Data Index: 510546 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 7.0368. Min Range: -7.0368

Max Act: 6.4488. Min Act: -0.0000

Data Index: 368857 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 7.0368. Min Range: -7.0368

Max Act: 6.3261. Min Act: -0.0000

Data Index: 747324 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 7.0368. Min Range: -7.0368

Max Act: 6.0605. Min Act: -0.0000

Data Index: 380728 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 7.0368. Min Range: -7.0368

Max Act: 5.8547. Min Act: -0.0000

Data Index: 996833 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 7.0368. Min Range: -7.0368

Max Act: 5.7970. Min Act: -0.0000

Data Index: 1289980 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 7.0368. Min Range: -7.0368

Max Act: 5.7128. Min Act: -0.0000

Data Index: 722516 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 7.0368. Min Range: -7.0368

Max Act: 5.8616. Min Act: -0.0000

Data Index: 892469 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 7.0368. Min Range: -7.0368

Max Act: 5.6356. Min Act: -0.0000

Data Index: 339953 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 7.0368. Min Range: -7.0368

Max Act: 5.5490. Min Act: -0.0000

Data Index: 626278 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 7.0368. Min Range: -7.0368

Max Act: 5.3077. Min Act: -0.0000

Data Index: 622165 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 7.0368. Min Range: -7.0368

Max Act: 5.2582. Min Act: -0.0000

Data Index: 825618 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 7.0368. Min Range: -7.0368

Max Act: 5.3919. Min Act: -0.0000

Data Index: 945980 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 7.0368. Min Range: -7.0368

Max Act: 4.7106. Min Act: -0.0000

Data Index: 698108 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 7.0368. Min Range: -7.0368

Max Act: 5.0278. Min Act: -0.0000

Data Index: 428829 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 7.0368. Min Range: -7.0368

Max Act: 4.8363. Min Act: -0.0000

Data Index: 857308 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 7.0368. Min Range: -7.0368

Max Act: 4.8701. Min Act: -0.0000

Data Index: 904468 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 7.0368. Min Range: -7.0368

Max Act: 4.6282. Min Act: -0.0000

Data Index: 706459 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 7.0368. Min Range: -7.0368

Max Act: 4.6097. Min Act: -0.0000

Data Index: 75632 (C4 (Web Text))

Max Activating Token Index: 688