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

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

Neuron 1400 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5185. Min Range: -1.5185

Max Act: 1.5185. Min Act: -0.0000

Data Index: 586963 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 1.5185. Min Range: -1.5185

Max Act: 1.2769. Min Act: -0.0000

Data Index: 867144 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.5185. Min Range: -1.5185

Max Act: 1.2528. Min Act: -0.0000

Data Index: 58270 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 1.5185. Min Range: -1.5185

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1252196 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 1.5185. Min Range: -1.5185

Max Act: 1.2199. Min Act: -0.0000

Data Index: 204837 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 1.5185. Min Range: -1.5185

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1034675 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.5185. Min Range: -1.5185

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1330798 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.9727. Min Act: -0.0000

Data Index: 767387 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.5185. Min Range: -1.5185

Max Act: 1.0830. Min Act: -0.0000

Data Index: 834122 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.9516. Min Act: -0.0000

Data Index: 966900 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1233220 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.9302. Min Act: -0.0000

Data Index: 293830 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1042574 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.7864. Min Act: -0.0000

Data Index: 283759 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1177936 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.8530. Min Act: -0.0000

Data Index: 397142 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.8528. Min Act: -0.0000

Data Index: 312635 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.8493. Min Act: -0.0000

Data Index: 75313 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1074823 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 1.5185. Min Range: -1.5185

Max Act: 0.7508. Min Act: -0.0000

Data Index: 560150 (C4 (Web Text))

Max Activating Token Index: 482