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

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

Neuron 899 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6019. Min Range: -3.6019

Max Act: 3.6019. Min Act: -0.0000

Data Index: 75482 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 3.6019. Min Range: -3.6019

Max Act: 2.9246. Min Act: -0.0000

Data Index: 382818 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 3.6019. Min Range: -3.6019

Max Act: 2.5801. Min Act: -0.0000

Data Index: 1514319 (Python Code)

Max Activating Token Index: 739

Text #3

Max Range: 3.6019. Min Range: -3.6019

Max Act: 2.4509. Min Act: -0.0000

Data Index: 613020 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 3.6019. Min Range: -3.6019

Max Act: 2.3695. Min Act: -0.0000

Data Index: 927355 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 3.6019. Min Range: -3.6019

Max Act: 2.1976. Min Act: -0.0000

Data Index: 1122992 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 3.6019. Min Range: -3.6019

Max Act: 2.2868. Min Act: -0.0000

Data Index: 1293884 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 3.6019. Min Range: -3.6019

Max Act: 2.2246. Min Act: -0.0000

Data Index: 251655 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.6019. Min Range: -3.6019

Max Act: 2.4320. Min Act: -0.0000

Data Index: 207163 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 3.6019. Min Range: -3.6019

Max Act: 1.8495. Min Act: -0.0000

Data Index: 484636 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 3.6019. Min Range: -3.6019

Max Act: 1.9228. Min Act: -0.0000

Data Index: 811226 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 3.6019. Min Range: -3.6019

Max Act: 2.0185. Min Act: -0.0000

Data Index: 147389 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 3.6019. Min Range: -3.6019

Max Act: 1.8972. Min Act: -0.0000

Data Index: 1343929 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 3.6019. Min Range: -3.6019

Max Act: 1.9844. Min Act: -0.0000

Data Index: 435247 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 3.6019. Min Range: -3.6019

Max Act: 1.7383. Min Act: -0.0000

Data Index: 714396 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 3.6019. Min Range: -3.6019

Max Act: 1.8146. Min Act: -0.0000

Data Index: 1045188 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 3.6019. Min Range: -3.6019

Max Act: 1.8828. Min Act: -0.0000

Data Index: 766300 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 3.6019. Min Range: -3.6019

Max Act: 1.6737. Min Act: -0.0000

Data Index: 728893 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 3.6019. Min Range: -3.6019

Max Act: 1.7806. Min Act: -0.0000

Data Index: 1334635 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 3.6019. Min Range: -3.6019

Max Act: 1.8353. Min Act: -0.0001

Data Index: 1004837 (C4 (Web Text))

Max Activating Token Index: 288