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

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

Neuron 4102 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.9745. Min Act: -0.0002

Data Index: 431036 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.9590. Min Act: -0.0002

Data Index: 1245433 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.9136. Min Act: -0.0002

Data Index: 40911 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.9218. Min Act: -0.0002

Data Index: 1070746 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8313. Min Act: -0.0003

Data Index: 1025537 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8413. Min Act: -0.0002

Data Index: 768814 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8373. Min Act: -0.0002

Data Index: 1086974 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8369. Min Act: -0.0002

Data Index: 290004 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8130. Min Act: -0.0002

Data Index: 252364 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7746. Min Act: -0.0002

Data Index: 207107 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7900. Min Act: -0.0002

Data Index: 734612 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7917. Min Act: -0.0002

Data Index: 958603 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7800. Min Act: -0.0002

Data Index: 1285487 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7893. Min Act: -0.0002

Data Index: 1136393 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7920. Min Act: -0.0002

Data Index: 684108 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7859. Min Act: -0.0002

Data Index: 1269220 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7817. Min Act: -0.0002

Data Index: 555342 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7705. Min Act: -0.0002

Data Index: 1344533 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7719. Min Act: -0.0002

Data Index: 57574 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7640. Min Act: -0.0002

Data Index: 246604 (C4 (Web Text))

Max Activating Token Index: 265