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

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

Neuron 4786 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3564. Min Act: -0.0001

Data Index: 1230495 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3718. Min Act: -0.0001

Data Index: 903694 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3200. Min Act: -0.0001

Data Index: 1263543 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2976. Min Act: -0.0001

Data Index: 382278 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3180. Min Act: -0.0001

Data Index: 1066785 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3508. Min Act: -0.0001

Data Index: 375789 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3125. Min Act: -0.0001

Data Index: 34937 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3103. Min Act: -0.0001

Data Index: 702207 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3027. Min Act: -0.0001

Data Index: 1290972 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2619. Min Act: -0.0001

Data Index: 1203668 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2783. Min Act: -0.0001

Data Index: 539169 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2804. Min Act: -0.0001

Data Index: 583987 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2600. Min Act: -0.0001

Data Index: 485230 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2912. Min Act: -0.0001

Data Index: 162320 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3177. Min Act: -0.0001

Data Index: 838572 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2777. Min Act: -0.0001

Data Index: 175504 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3227. Min Act: -0.0001

Data Index: 874869 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1199475 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2647. Min Act: -0.0001

Data Index: 1086226 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2696. Min Act: -0.0001

Data Index: 634865 (C4 (Web Text))

Max Activating Token Index: 161