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

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

Neuron 4083 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4467. Min Range: -1.4467

Max Act: 1.4467. Min Act: -0.0000

Data Index: 549865 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 1.4467. Min Range: -1.4467

Max Act: 1.1435. Min Act: -0.0000

Data Index: 773887 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 1.4467. Min Range: -1.4467

Max Act: 1.0818. Min Act: -0.0000

Data Index: 858740 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 1.4467. Min Range: -1.4467

Max Act: 1.0110. Min Act: -0.0000

Data Index: 860772 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1116264 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 1.4467. Min Range: -1.4467

Max Act: 1.0009. Min Act: -0.0000

Data Index: 521173 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.8834. Min Act: -0.0000

Data Index: 221431 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1231511 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.8684. Min Act: -0.0000

Data Index: 521085 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.8635. Min Act: -0.0000

Data Index: 660879 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.7801. Min Act: -0.0000

Data Index: 792288 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.8748. Min Act: -0.0000

Data Index: 1010607 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.8264. Min Act: -0.0000

Data Index: 998552 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1230565 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1144043 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.7886. Min Act: -0.0000

Data Index: 511206 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.7209. Min Act: -0.0000

Data Index: 843642 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1161166 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.7848. Min Act: -0.0000

Data Index: 750525 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.4467. Min Range: -1.4467

Max Act: 0.7233. Min Act: -0.0000

Data Index: 831845 (C4 (Web Text))

Max Activating Token Index: 702