Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2105 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.6565. Min Act: -0.0000

Data Index: 389109 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.6358. Min Act: -0.0000

Data Index: 123483 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.6874. Min Act: -0.0000

Data Index: 865573 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.6068. Min Act: -0.0000

Data Index: 719803 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1329939 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5839. Min Act: -0.0000

Data Index: 528511 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1599069 (Python Code)

Max Activating Token Index: 54

Text #7

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5925. Min Act: -0.0000

Data Index: 186682 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5418. Min Act: -0.0000

Data Index: 354959 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5838. Min Act: -0.0000

Data Index: 97668 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1155791 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5419. Min Act: -0.0000

Data Index: 899757 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5604. Min Act: -0.0000

Data Index: 947900 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1634667 (Python Code)

Max Activating Token Index: 926

Text #14

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5788. Min Act: -0.0000

Data Index: 705188 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1150196 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1142730 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5358. Min Act: -0.0000

Data Index: 207293 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1578931 (Python Code)

Max Activating Token Index: 492

Text #19

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5434. Min Act: -0.0000

Data Index: 672238 (C4 (Web Text))

Max Activating Token Index: 741