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

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

Neuron 644 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: 0.6449. Min Range: -0.6449

Max Act: 0.6449. Min Act: -0.0001

Data Index: 612749 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.5949. Min Act: -0.0001

Data Index: 1349186 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.6079. Min Act: -0.0001

Data Index: 665148 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.6224. Min Act: -0.0001

Data Index: 560264 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.5650. Min Act: -0.0001

Data Index: 472878 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.5417. Min Act: -0.0001

Data Index: 589395 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.5013. Min Act: -0.0001

Data Index: 641986 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4934. Min Act: -0.0001

Data Index: 209058 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4696. Min Act: -0.0000

Data Index: 740307 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4526. Min Act: -0.0000

Data Index: 890165 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4756. Min Act: -0.0001

Data Index: 616018 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4572. Min Act: -0.0000

Data Index: 896935 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4633. Min Act: -0.0001

Data Index: 138064 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1093465 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4764. Min Act: -0.0001

Data Index: 18878 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4503. Min Act: -0.0001

Data Index: 839773 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4500. Min Act: -0.0001

Data Index: 951053 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4760. Min Act: -0.0000

Data Index: 814606 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4592. Min Act: -0.0000

Data Index: 931054 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.6449. Min Range: -0.6449

Max Act: 0.4453. Min Act: -0.0001

Data Index: 618385 (C4 (Web Text))

Max Activating Token Index: 545