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

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

Neuron 1175 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6892. Min Act: -0.0000

Data Index: 81404 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.7724. Min Act: -0.0000

Data Index: 95762 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1640423 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6681. Min Act: -0.0000

Data Index: 271985 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.7244. Min Act: -0.0000

Data Index: 895959 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6554. Min Act: -0.0000

Data Index: 736163 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1194736 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6531. Min Act: -0.0000

Data Index: 451203 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6112. Min Act: -0.0000

Data Index: 118487 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6909. Min Act: -0.0000

Data Index: 41242 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6676. Min Act: -0.0000

Data Index: 853884 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.7096. Min Act: -0.0000

Data Index: 210505 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6417. Min Act: -0.0001

Data Index: 1259980 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6114. Min Act: -0.0000

Data Index: 681523 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6697. Min Act: -0.0000

Data Index: 631549 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6889. Min Act: -0.0000

Data Index: 193903 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1319828 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6241. Min Act: -0.0000

Data Index: 499951 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1339010 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.7724. Min Range: -0.7724

Max Act: 0.6672. Min Act: -0.0000

Data Index: 5122 (C4 (Web Text))

Max Activating Token Index: 169