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

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

Neuron 5330 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: 0.9548. Min Range: -0.9548

Max Act: 0.9548. Min Act: -0.0000

Data Index: 43751 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.9010. Min Act: -0.0000

Data Index: 800092 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.8632. Min Act: -0.0000

Data Index: 113844 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1179160 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7965. Min Act: -0.0000

Data Index: 312105 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1146979 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7433. Min Act: -0.0000

Data Index: 497012 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7766. Min Act: -0.0000

Data Index: 215682 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1010664 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6797. Min Act: -0.0000

Data Index: 43724 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1321259 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7355. Min Act: -0.0000

Data Index: 994993 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7124. Min Act: -0.0000

Data Index: 979541 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7112. Min Act: -0.0000

Data Index: 349249 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1080508 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.7187. Min Act: -0.0000

Data Index: 129418 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6875. Min Act: -0.0000

Data Index: 117539 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6912. Min Act: -0.0000

Data Index: 305864 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6897. Min Act: -0.0000

Data Index: 454747 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.9548. Min Range: -0.9548

Max Act: 0.6912. Min Act: -0.0000

Data Index: 957308 (C4 (Web Text))

Max Activating Token Index: 836