Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 106 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.6518. Min Act: -0.0000

Data Index: 525668 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1164142 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.5890. Min Act: -0.0001

Data Index: 176344 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1343152 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.5966. Min Act: -0.0000

Data Index: 661960 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.5497. Min Act: -0.0000

Data Index: 875278 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.5430. Min Act: -0.0000

Data Index: 874307 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.5450. Min Act: -0.0000

Data Index: 426053 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.5135. Min Act: -0.0001

Data Index: 868726 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.5236. Min Act: -0.0001

Data Index: 789007 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.5193. Min Act: -0.0000

Data Index: 722260 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1340107 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.4873. Min Act: -0.0001

Data Index: 148187 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.4680. Min Act: -0.0000

Data Index: 646689 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.4649. Min Act: -0.0000

Data Index: 902727 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1053397 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.4562. Min Act: -0.0001

Data Index: 73376 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1097345 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.4389. Min Act: -0.0001

Data Index: 1022145 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.6527. Min Range: -0.6527

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1081793 (C4 (Web Text))

Max Activating Token Index: 995