Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3227 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.1040. Min Act: -0.0001

Data Index: 640778 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0643. Min Act: -0.0001

Data Index: 394561 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0385. Min Act: -0.0001

Data Index: 787164 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0528. Min Act: -0.0001

Data Index: 1316083 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0112. Min Act: -0.0001

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9831. Min Act: -0.0001

Data Index: 149216 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0110. Min Act: -0.0001

Data Index: 1279915 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9830. Min Act: -0.0001

Data Index: 964066 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9445. Min Act: -0.0001

Data Index: 779287 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1228887 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9662. Min Act: -0.0001

Data Index: 635207 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9334. Min Act: -0.0001

Data Index: 932809 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9496. Min Act: -0.0001

Data Index: 799447 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9371. Min Act: -0.0001

Data Index: 379246 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9119. Min Act: -0.0001

Data Index: 1113865 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9314. Min Act: -0.0001

Data Index: 131557 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9092. Min Act: -0.0001

Data Index: 1046779 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9334. Min Act: -0.0001

Data Index: 437126 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9301. Min Act: -0.0001

Data Index: 195915 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9243. Min Act: -0.0001

Data Index: 491304 (C4 (Web Text))

Max Activating Token Index: 722