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

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

Neuron 1458 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: 0.9103. Min Range: -0.9103

Max Act: 0.9103. Min Act: -0.0001

Data Index: 749334 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.8855. Min Act: -0.0001

Data Index: 1656713 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7468. Min Act: -0.0001

Data Index: 1561094 (Python Code)

Max Activating Token Index: 530

Text #3

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6961. Min Act: -0.0001

Data Index: 1100093 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7316. Min Act: -0.0001

Data Index: 265454 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6898. Min Act: -0.0000

Data Index: 932239 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6569. Min Act: -0.0001

Data Index: 1447546 (Python Code)

Max Activating Token Index: 728

Text #7

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.4942. Min Act: -0.0000

Data Index: 164340 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1277713 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6078. Min Act: -0.0000

Data Index: 20690 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6348. Min Act: -0.0001

Data Index: 876010 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6221. Min Act: -0.0001

Data Index: 1035721 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1565371 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1263076 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6571. Min Act: -0.0001

Data Index: 179363 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.5329. Min Act: -0.0001

Data Index: 1488520 (Python Code)

Max Activating Token Index: 253

Text #16

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6692. Min Act: -0.0001

Data Index: 1051802 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6012. Min Act: -0.0001

Data Index: 517800 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1064842 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.4962. Min Act: -0.0001

Data Index: 753813 (C4 (Web Text))

Max Activating Token Index: 731