Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2688 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.9426. Min Act: -0.0001

Data Index: 798753 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.8247. Min Act: -0.0000

Data Index: 610039 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.7399. Min Act: -0.0000

Data Index: 819009 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.7953. Min Act: -0.0001

Data Index: 249858 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.8548. Min Act: -0.0001

Data Index: 419873 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.7154. Min Act: -0.0001

Data Index: 153 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.5072. Min Act: -0.0001

Data Index: 710524 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.5717. Min Act: -0.0001

Data Index: 1117461 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.5251. Min Act: -0.0001

Data Index: 749711 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.6029. Min Act: -0.0001

Data Index: 123526 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.5049. Min Act: -0.0001

Data Index: 860211 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.3979. Min Act: -0.0001

Data Index: 116154 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.4930. Min Act: -0.0001

Data Index: 1129328 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.5179. Min Act: -0.0001

Data Index: 30487 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.5114. Min Act: -0.0001

Data Index: 924788 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.4207. Min Act: -0.0001

Data Index: 965841 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.3291. Min Act: -0.0001

Data Index: 723720 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.3307. Min Act: -0.0001

Data Index: 804064 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.3215. Min Act: -0.0001

Data Index: 785493 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.2973. Min Act: -0.0000

Data Index: 650693 (C4 (Web Text))

Max Activating Token Index: 799