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

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

Neuron 955 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8698. Min Range: -4.8698

Max Act: 4.8698. Min Act: -0.0001

Data Index: 732045 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 4.8698. Min Range: -4.8698

Max Act: 4.5190. Min Act: -0.0000

Data Index: 411036 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 4.8698. Min Range: -4.8698

Max Act: 4.2283. Min Act: -0.0000

Data Index: 556606 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 4.8698. Min Range: -4.8698

Max Act: 4.0373. Min Act: -0.0000

Data Index: 1436248 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 4.8698. Min Range: -4.8698

Max Act: 3.9077. Min Act: -0.0000

Data Index: 4223 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 4.8698. Min Range: -4.8698

Max Act: 3.6585. Min Act: -0.0000

Data Index: 868172 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 4.8698. Min Range: -4.8698

Max Act: 3.2806. Min Act: -0.0000

Data Index: 177157 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 4.8698. Min Range: -4.8698

Max Act: 3.3505. Min Act: -0.0000

Data Index: 1176700 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 4.8698. Min Range: -4.8698

Max Act: 3.3112. Min Act: -0.0001

Data Index: 612591 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 4.8698. Min Range: -4.8698

Max Act: 3.2527. Min Act: -0.0000

Data Index: 7087 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 4.8698. Min Range: -4.8698

Max Act: 3.3815. Min Act: -0.0000

Data Index: 472235 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 4.8698. Min Range: -4.8698

Max Act: 3.3932. Min Act: -0.0001

Data Index: 1203653 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 4.8698. Min Range: -4.8698

Max Act: 3.0568. Min Act: -0.0001

Data Index: 206236 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 4.8698. Min Range: -4.8698

Max Act: 2.7737. Min Act: -0.0001

Data Index: 677542 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 4.8698. Min Range: -4.8698

Max Act: 2.9626. Min Act: -0.0000

Data Index: 704447 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 4.8698. Min Range: -4.8698

Max Act: 2.8063. Min Act: -0.0000

Data Index: 112730 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 4.8698. Min Range: -4.8698

Max Act: 2.9330. Min Act: -0.0001

Data Index: 270480 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 4.8698. Min Range: -4.8698

Max Act: 3.0453. Min Act: -0.0000

Data Index: 690050 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 4.8698. Min Range: -4.8698

Max Act: 2.7558. Min Act: -0.0001

Data Index: 360680 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 4.8698. Min Range: -4.8698

Max Act: 2.9275. Min Act: -0.0000

Data Index: 204393 (C4 (Web Text))

Max Activating Token Index: 203