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

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

Neuron 1829 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2783. Min Range: -1.2783

Max Act: 1.2783. Min Act: -0.0000

Data Index: 974997 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.8664. Min Act: -0.0000

Data Index: 46732 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1327173 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.7927. Min Act: -0.0000

Data Index: 701373 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.7898. Min Act: -0.0000

Data Index: 92280 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1084855 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1006336 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1002984 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.7158. Min Act: -0.0000

Data Index: 890582 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.6796. Min Act: -0.0000

Data Index: 118532 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1142709 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.7171. Min Act: -0.0000

Data Index: 126685 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.6391. Min Act: -0.0000

Data Index: 308988 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1329218 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.6943. Min Act: -0.0000

Data Index: 990496 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.6558. Min Act: -0.0000

Data Index: 562951 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.6106. Min Act: -0.0000

Data Index: 268047 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.6337. Min Act: -0.0000

Data Index: 774468 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.5999. Min Act: -0.0000

Data Index: 823198 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.2783. Min Range: -1.2783

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1207336 (C4 (Web Text))

Max Activating Token Index: 78