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

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

Neuron 5192 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: 0.8873. Min Range: -0.8873

Max Act: 0.8865. Min Act: -0.0000

Data Index: 643751 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.8873. Min Act: -0.0000

Data Index: 853267 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.8873. Min Act: -0.0000

Data Index: 66997 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7801. Min Act: -0.0000

Data Index: 998941 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7532. Min Act: -0.0000

Data Index: 77394 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.8108. Min Act: -0.0000

Data Index: 578069 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7849. Min Act: -0.0000

Data Index: 901573 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7862. Min Act: -0.0000

Data Index: 98219 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7642. Min Act: -0.0000

Data Index: 870713 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6853. Min Act: -0.0000

Data Index: 581866 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1174159 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1115494 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1008530 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6313. Min Act: -0.0000

Data Index: 466370 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6096. Min Act: -0.0000

Data Index: 361180 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5839. Min Act: -0.0000

Data Index: 435104 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5424. Min Act: -0.0000

Data Index: 220424 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5913. Min Act: -0.0000

Data Index: 366855 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5718. Min Act: -0.0000

Data Index: 285537 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5706. Min Act: -0.0000

Data Index: 534725 (C4 (Web Text))

Max Activating Token Index: 91