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

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

Neuron 853 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: 0.3349. Min Range: -0.3349

Max Act: 0.3310. Min Act: -0.0003

Data Index: 281347 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3349. Min Act: -0.0003

Data Index: 987760 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3280. Min Act: -0.0003

Data Index: 911476 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2955. Min Act: -0.0003

Data Index: 107982 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3204. Min Act: -0.0003

Data Index: 275108 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3023. Min Act: -0.0003

Data Index: 1193718 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3108. Min Act: -0.0003

Data Index: 1183491 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3178. Min Act: -0.0003

Data Index: 1157050 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3028. Min Act: -0.0003

Data Index: 995385 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3044. Min Act: -0.0003

Data Index: 1314228 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2931. Min Act: -0.0003

Data Index: 183230 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3047. Min Act: -0.0003

Data Index: 964912 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3098. Min Act: -0.0003

Data Index: 582315 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2975. Min Act: -0.0003

Data Index: 260396 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2909. Min Act: -0.0003

Data Index: 432949 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2812. Min Act: -0.0003

Data Index: 1262130 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3029. Min Act: -0.0003

Data Index: 237267 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2973. Min Act: -0.0003

Data Index: 1007690 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2768. Min Act: -0.0003

Data Index: 1113479 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3029. Min Act: -0.0003

Data Index: 219385 (C4 (Web Text))

Max Activating Token Index: 913