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

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

Neuron 4192 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: 2.0087. Min Range: -2.0087

Max Act: 2.0087. Min Act: -0.0000

Data Index: 419987 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.8676. Min Act: -0.0000

Data Index: 969611 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.8327. Min Act: -0.0000

Data Index: 618025 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.7767. Min Act: -0.0000

Data Index: 905668 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.7620. Min Act: -0.0000

Data Index: 1260589 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.8410. Min Act: -0.0000

Data Index: 939989 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.7127. Min Act: -0.0000

Data Index: 988413 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.5593. Min Act: -0.0000

Data Index: 968164 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.5586. Min Act: -0.0000

Data Index: 872434 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.5641. Min Act: -0.0000

Data Index: 533665 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.4151. Min Act: -0.0000

Data Index: 609039 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.5413. Min Act: -0.0000

Data Index: 335534 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.5658. Min Act: -0.0000

Data Index: 1043015 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.3782. Min Act: -0.0000

Data Index: 471362 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.4293. Min Act: -0.0000

Data Index: 630248 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.3308. Min Act: -0.0000

Data Index: 642385 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.3101. Min Act: -0.0000

Data Index: 562884 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.2083. Min Act: -0.0000

Data Index: 906331 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.1987. Min Act: -0.0000

Data Index: 164239 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 2.0087. Min Range: -2.0087

Max Act: 1.2496. Min Act: -0.0000

Data Index: 275147 (C4 (Web Text))

Max Activating Token Index: 751