Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4748 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.2558. Min Act: -0.0001

Data Index: 507244 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.0121. Min Act: -0.0001

Data Index: 666875 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.6057. Min Act: -0.0000

Data Index: 903112 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.6079. Min Act: -0.0001

Data Index: 640833 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.5905. Min Act: -0.0001

Data Index: 1237614 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.4461. Min Act: -0.0001

Data Index: 113323 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.4199. Min Act: -0.0001

Data Index: 1183049 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.2679. Min Act: -0.0001

Data Index: 536064 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.2348. Min Act: -0.0001

Data Index: 1243585 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.1787. Min Act: -0.0001

Data Index: 1618047 (Python Code)

Max Activating Token Index: 971

Text #10

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.2386. Min Act: -0.0001

Data Index: 482654 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.2450. Min Act: -0.0001

Data Index: 419951 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.1124. Min Act: -0.0001

Data Index: 502106 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.0899. Min Act: -0.0001

Data Index: 791017 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.0633. Min Act: -0.0001

Data Index: 1040179 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.2077. Min Act: -0.0001

Data Index: 617195 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.3075. Min Act: -0.0001

Data Index: 310390 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.0769. Min Act: -0.0001

Data Index: 466172 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.3047. Min Act: -0.0001

Data Index: 446313 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.1706. Min Act: -0.0001

Data Index: 912283 (C4 (Web Text))

Max Activating Token Index: 13