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

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

Neuron 4401 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: 6.4713. Min Range: -6.4713

Max Act: 6.3932. Min Act: -0.0001

Data Index: 349178 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 6.4713. Min Range: -6.4713

Max Act: 6.4713. Min Act: -0.0000

Data Index: 380858 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 6.4713. Min Range: -6.4713

Max Act: 5.0052. Min Act: -0.0000

Data Index: 1356484 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.8401. Min Act: -0.0000

Data Index: 704126 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 6.4713. Min Range: -6.4713

Max Act: 5.0366. Min Act: -0.0000

Data Index: 751408 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.7659. Min Act: -0.0000

Data Index: 990138 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.5795. Min Act: -0.0001

Data Index: 443082 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.7362. Min Act: -0.0001

Data Index: 740818 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.8245. Min Act: -0.0000

Data Index: 178687 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 6.4713. Min Range: -6.4713

Max Act: 5.0225. Min Act: -0.0000

Data Index: 448350 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.4550. Min Act: -0.0001

Data Index: 905994 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.0454. Min Act: -0.0000

Data Index: 47444 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.3973. Min Act: -0.0000

Data Index: 122843 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.0394. Min Act: -0.0000

Data Index: 611280 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.2906. Min Act: -0.0000

Data Index: 969097 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.2879. Min Act: -0.0000

Data Index: 720077 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.0675. Min Act: -0.0000

Data Index: 963330 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.0424. Min Act: -0.0001

Data Index: 366020 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 6.4713. Min Range: -6.4713

Max Act: 4.3641. Min Act: -0.0001

Data Index: 577414 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 6.4713. Min Range: -6.4713

Max Act: 3.9579. Min Act: -0.0000

Data Index: 502017 (C4 (Web Text))

Max Activating Token Index: 23