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

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

Neuron 2616 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9950. Min Act: -0.0000

Data Index: 43166 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9814. Min Act: -0.0000

Data Index: 191709 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.7930. Min Act: -0.0000

Data Index: 318817 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.7368. Min Act: -0.0000

Data Index: 1634774 (Python Code)

Max Activating Token Index: 304

Text #4

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.6332. Min Act: -0.0000

Data Index: 1515122 (Python Code)

Max Activating Token Index: 763

Text #5

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.7303. Min Act: -0.0000

Data Index: 1514984 (Python Code)

Max Activating Token Index: 405

Text #6

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.6063. Min Act: -0.0000

Data Index: 1105389 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.6581. Min Act: -0.0000

Data Index: 711850 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.7090. Min Act: -0.0000

Data Index: 1460894 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.6109. Min Act: -0.0000

Data Index: 1624321 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.8580. Min Act: -0.0000

Data Index: 945634 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.5809. Min Act: -0.0000

Data Index: 1141048 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.6084. Min Act: -0.0000

Data Index: 764094 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.4030. Min Act: -0.0000

Data Index: 563118 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.5179. Min Act: -0.0000

Data Index: 381988 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.4183. Min Act: -0.0000

Data Index: 715361 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.5602. Min Act: -0.0000

Data Index: 967041 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.4187. Min Act: -0.0000

Data Index: 1376084 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.5507. Min Act: -0.0000

Data Index: 739775 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.5757. Min Act: -0.0000

Data Index: 1219724 (C4 (Web Text))

Max Activating Token Index: 70