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

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

Neuron 4087 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: 0.8272. Min Range: -0.8272

Max Act: 0.8171. Min Act: -0.0000

Data Index: 650634 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1280526 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.8272. Min Act: -0.0000

Data Index: 600114 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.7599. Min Act: -0.0000

Data Index: 360803 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.7384. Min Act: -0.0001

Data Index: 682058 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1036734 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.7408. Min Act: -0.0000

Data Index: 281410 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.7414. Min Act: -0.0000

Data Index: 827262 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.7003. Min Act: -0.0000

Data Index: 591107 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1353479 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1063927 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6718. Min Act: -0.0000

Data Index: 87825 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6623. Min Act: -0.0001

Data Index: 556258 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1213589 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6734. Min Act: -0.0001

Data Index: 538809 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6881. Min Act: -0.0001

Data Index: 1163904 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1264602 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6173. Min Act: -0.0000

Data Index: 619745 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6885. Min Act: -0.0000

Data Index: 183352 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6853. Min Act: -0.0000

Data Index: 433372 (C4 (Web Text))

Max Activating Token Index: 841