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

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

Neuron 572 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: 1.2334. Min Range: -1.2334

Max Act: 1.2334. Min Act: -0.0000

Data Index: 348375 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.2334. Min Range: -1.2334

Max Act: 1.0769. Min Act: -0.0000

Data Index: 243714 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.9662. Min Act: -0.0000

Data Index: 948616 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.9915. Min Act: -0.0000

Data Index: 776786 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 1.2334. Min Range: -1.2334

Max Act: 1.0392. Min Act: -0.0000

Data Index: 340293 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.9140. Min Act: -0.0000

Data Index: 145045 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1157454 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1369508 (Python Code)

Max Activating Token Index: 264

Text #8

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.9641. Min Act: -0.0000

Data Index: 662941 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1559173 (Python Code)

Max Activating Token Index: 640

Text #10

Max Range: 1.2334. Min Range: -1.2334

Max Act: 1.0148. Min Act: -0.0000

Data Index: 24059 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.8865. Min Act: -0.0000

Data Index: 901150 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.8855. Min Act: -0.0000

Data Index: 108151 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1417975 (Python Code)

Max Activating Token Index: 162

Text #14

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.9045. Min Act: -0.0000

Data Index: 51913 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1523061 (Python Code)

Max Activating Token Index: 113

Text #16

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1604647 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1421687 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1169774 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1015602 (C4 (Web Text))

Max Activating Token Index: 883