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

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

Neuron 3747 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: 0.7586. Min Range: -0.7586

Max Act: 0.7586. Min Act: -0.0000

Data Index: 19229 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.7048. Min Act: -0.0000

Data Index: 879769 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1350156 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1373074 (Python Code)

Max Activating Token Index: 518

Text #4

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6507. Min Act: -0.0000

Data Index: 149692 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6575. Min Act: -0.0000

Data Index: 830880 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6175. Min Act: -0.0000

Data Index: 792391 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1028337 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1411343 (Python Code)

Max Activating Token Index: 986

Text #9

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1085547 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6352. Min Act: -0.0000

Data Index: 599936 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1505169 (Python Code)

Max Activating Token Index: 875

Text #12

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5848. Min Act: -0.0000

Data Index: 660416 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1300155 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1174757 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1503627 (Python Code)

Max Activating Token Index: 762

Text #16

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1543135 (Python Code)

Max Activating Token Index: 851

Text #17

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5836. Min Act: -0.0000

Data Index: 139185 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6172. Min Act: -0.0000

Data Index: 195095 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5546. Min Act: -0.0000

Data Index: 439606 (C4 (Web Text))

Max Activating Token Index: 958