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

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

Neuron 3960 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7648. Min Range: -3.7648

Max Act: 3.7648. Min Act: -0.0000

Data Index: 534413 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 3.7648. Min Range: -3.7648

Max Act: 3.1493. Min Act: -0.0000

Data Index: 1343516 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 3.7648. Min Range: -3.7648

Max Act: 3.2480. Min Act: -0.0000

Data Index: 1265224 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.9492. Min Act: -0.0000

Data Index: 565115 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 3.7648. Min Range: -3.7648

Max Act: 3.0459. Min Act: -0.0000

Data Index: 1295010 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 3.7648. Min Range: -3.7648

Max Act: 3.1722. Min Act: -0.0000

Data Index: 1016726 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.9898. Min Act: -0.0000

Data Index: 871599 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.7316. Min Act: -0.0000

Data Index: 583617 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 3.7648. Min Range: -3.7648

Max Act: 3.1850. Min Act: -0.0000

Data Index: 875423 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.9194. Min Act: -0.0000

Data Index: 107006 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.9175. Min Act: -0.0000

Data Index: 467710 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 3.7648. Min Range: -3.7648

Max Act: 3.3083. Min Act: -0.0000

Data Index: 493496 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 3.7648. Min Range: -3.7648

Max Act: 3.0435. Min Act: -0.0000

Data Index: 358264 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.5620. Min Act: -0.0000

Data Index: 1152932 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.4110. Min Act: -0.0000

Data Index: 306930 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.6658. Min Act: -0.0000

Data Index: 659913 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.7069. Min Act: -0.0000

Data Index: 1044391 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.9932. Min Act: -0.0000

Data Index: 126744 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.6024. Min Act: -0.0000

Data Index: 397043 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 3.7648. Min Range: -3.7648

Max Act: 2.4234. Min Act: -0.0000

Data Index: 25070 (C4 (Web Text))

Max Activating Token Index: 189