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

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

Neuron 2566 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.8450. Min Act: -0.0000

Data Index: 431536 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1215418 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.7569. Min Act: 0.0000

Data Index: 250086 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.7170. Min Act: -0.0000

Data Index: 612034 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1263332 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6688. Min Act: -0.0000

Data Index: 508779 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6845. Min Act: -0.0000

Data Index: 40124 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6787. Min Act: -0.0000

Data Index: 23049 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6140. Min Act: 0.0000

Data Index: 814023 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5764. Min Act: -0.0000

Data Index: 500908 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5696. Min Act: -0.0000

Data Index: 217708 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1125595 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1097899 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5533. Min Act: -0.0000

Data Index: 730966 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5512. Min Act: 0.0000

Data Index: 1129549 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5232. Min Act: -0.0000

Data Index: 867536 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1326416 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.4956. Min Act: -0.0000

Data Index: 96416 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1144333 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1559112 (Python Code)

Max Activating Token Index: 515