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

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

Neuron 4368 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: 4.4222. Min Range: -4.4222

Max Act: 4.4222. Min Act: -0.0000

Data Index: 237857 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 4.4222. Min Range: -4.4222

Max Act: 4.4216. Min Act: -0.0000

Data Index: 106823 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 4.4222. Min Range: -4.4222

Max Act: 4.2239. Min Act: -0.0000

Data Index: 477702 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.6664. Min Act: -0.0000

Data Index: 579572 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.7645. Min Act: -0.0000

Data Index: 752504 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.9852. Min Act: -0.0000

Data Index: 345893 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.7993. Min Act: -0.0000

Data Index: 327516 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.7028. Min Act: -0.0000

Data Index: 1077262 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.7088. Min Act: -0.0000

Data Index: 661502 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.5517. Min Act: -0.0000

Data Index: 655490 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.8167. Min Act: -0.0000

Data Index: 200158 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.3676. Min Act: -0.0000

Data Index: 99848 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.5420. Min Act: -0.0000

Data Index: 606871 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.6445. Min Act: -0.0000

Data Index: 391358 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.4043. Min Act: -0.0000

Data Index: 50453 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.4157. Min Act: -0.0000

Data Index: 566113 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.3861. Min Act: -0.0000

Data Index: 724890 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.3683. Min Act: -0.0000

Data Index: 222474 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.1943. Min Act: -0.0000

Data Index: 1221096 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 4.4222. Min Range: -4.4222

Max Act: 3.1924. Min Act: -0.0000

Data Index: 803519 (C4 (Web Text))

Max Activating Token Index: 23