Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2605 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1526813 (Python Code)

Max Activating Token Index: 605

Text #1

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.5362. Min Act: -0.0001

Data Index: 184985 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1567726 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1391961 (Python Code)

Max Activating Token Index: 165

Text #4

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1507178 (Python Code)

Max Activating Token Index: 546

Text #5

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4148. Min Act: -0.0001

Data Index: 1119925 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1378702 (Python Code)

Max Activating Token Index: 222

Text #7

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4168. Min Act: -0.0000

Data Index: 124745 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4032. Min Act: -0.0001

Data Index: 1275663 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1384250 (Python Code)

Max Activating Token Index: 629

Text #10

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1654854 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1372265 (Python Code)

Max Activating Token Index: 943

Text #12

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1429775 (Python Code)

Max Activating Token Index: 608

Text #13

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1532454 (Python Code)

Max Activating Token Index: 494

Text #14

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.3688. Min Act: -0.0001

Data Index: 1472699 (Python Code)

Max Activating Token Index: 404

Text #15

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1437870 (Python Code)

Max Activating Token Index: 131

Text #16

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.3780. Min Act: -0.0000

Data Index: 254086 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1369174 (Python Code)

Max Activating Token Index: 1002

Text #18

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.3602. Min Act: -0.0000

Data Index: 1642745 (Python Code)

Max Activating Token Index: 637

Text #19

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.3651. Min Act: -0.0001

Data Index: 290366 (C4 (Web Text))

Max Activating Token Index: 433