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

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

Neuron 2966 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: 4.1154. Min Range: -4.1154

Max Act: 4.1154. Min Act: -0.0001

Data Index: 1625256 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 4.1154. Min Range: -4.1154

Max Act: 4.0807. Min Act: -0.0001

Data Index: 1145129 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 4.1154. Min Range: -4.1154

Max Act: 4.0018. Min Act: -0.0001

Data Index: 904771 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 4.1154. Min Range: -4.1154

Max Act: 3.5136. Min Act: -0.0001

Data Index: 56721 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 4.1154. Min Range: -4.1154

Max Act: 3.1522. Min Act: -0.0001

Data Index: 1586297 (Python Code)

Max Activating Token Index: 358

Text #5

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.7370. Min Act: -0.0001

Data Index: 314367 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 4.1154. Min Range: -4.1154

Max Act: 3.1728. Min Act: -0.0001

Data Index: 509000 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.8728. Min Act: -0.0001

Data Index: 1134329 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.8254. Min Act: -0.0001

Data Index: 1015389 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.9084. Min Act: -0.0000

Data Index: 194894 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.8708. Min Act: -0.0000

Data Index: 606488 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.6417. Min Act: -0.0000

Data Index: 1001423 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.8234. Min Act: -0.0000

Data Index: 1029227 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.5978. Min Act: -0.0000

Data Index: 421525 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.7048. Min Act: -0.0000

Data Index: 365171 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.4363. Min Act: -0.0001

Data Index: 303409 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.6700. Min Act: -0.0000

Data Index: 922858 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.3696. Min Act: -0.0001

Data Index: 1010964 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.5003. Min Act: -0.0001

Data Index: 985676 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 4.1154. Min Range: -4.1154

Max Act: 2.4880. Min Act: -0.0000

Data Index: 477152 (C4 (Web Text))

Max Activating Token Index: 473