Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2823 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.3068. Min Act: -0.0003

Data Index: 221514 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2887. Min Act: -0.0002

Data Index: 106306 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2940. Min Act: -0.0003

Data Index: 1306889 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2706. Min Act: -0.0003

Data Index: 51848 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2777. Min Act: -0.0003

Data Index: 500216 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2593. Min Act: -0.0003

Data Index: 857161 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2646. Min Act: -0.0002

Data Index: 1166999 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2422. Min Act: -0.0002

Data Index: 1240000 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2776. Min Act: -0.0003

Data Index: 1291730 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2271. Min Act: -0.0003

Data Index: 863085 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.3058. Min Act: -0.0002

Data Index: 617649 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2673. Min Act: -0.0002

Data Index: 1155537 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.3109. Min Act: -0.0003

Data Index: 298919 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2524. Min Act: -0.0003

Data Index: 1097210 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2790. Min Act: -0.0003

Data Index: 506471 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2570. Min Act: -0.0003

Data Index: 1010782 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2455. Min Act: -0.0003

Data Index: 448836 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2480. Min Act: -0.0003

Data Index: 1051194 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2306. Min Act: -0.0003

Data Index: 867144 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2528. Min Act: -0.0003

Data Index: 590917 (C4 (Web Text))

Max Activating Token Index: 175