Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2174 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.2602. Min Act: -0.0001

Data Index: 636826 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1632. Min Act: -0.0001

Data Index: 1270966 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.9148. Min Act: -0.0001

Data Index: 1008965 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.9022. Min Act: -0.0001

Data Index: 1278651 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.8455. Min Act: -0.0001

Data Index: 829822 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.8632. Min Act: -0.0001

Data Index: 83406 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.8767. Min Act: -0.0001

Data Index: 279185 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.8711. Min Act: -0.0001

Data Index: 990204 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.7591. Min Act: -0.0001

Data Index: 1295496 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.8090. Min Act: -0.0001

Data Index: 220117 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.7431. Min Act: -0.0001

Data Index: 371623 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.7053. Min Act: -0.0001

Data Index: 327934 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.6467. Min Act: -0.0001

Data Index: 768144 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.6487. Min Act: -0.0001

Data Index: 134699 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.4411. Min Act: -0.0001

Data Index: 855999 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.6221. Min Act: -0.0001

Data Index: 2747 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.5790. Min Act: -0.0001

Data Index: 360057 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.5548. Min Act: -0.0001

Data Index: 408915 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.5348. Min Act: -0.0001

Data Index: 69690 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 1.2602. Min Range: -1.2602

Max Act: 0.6299. Min Act: -0.0001

Data Index: 866801 (C4 (Web Text))

Max Activating Token Index: 425