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

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

Neuron 3696 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: 0.9973. Min Range: -0.9973

Max Act: 0.9973. Min Act: -0.0000

Data Index: 1251380 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1138190 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.8161. Min Act: -0.0000

Data Index: 205019 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7875. Min Act: -0.0000

Data Index: 613634 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7842. Min Act: -0.0000

Data Index: 160445 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1620976 (Python Code)

Max Activating Token Index: 737

Text #6

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1504155 (Python Code)

Max Activating Token Index: 938

Text #7

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1588383 (Python Code)

Max Activating Token Index: 799

Text #8

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.5778. Min Act: -0.0000

Data Index: 93797 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6655. Min Act: -0.0000

Data Index: 629292 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1588117 (Python Code)

Max Activating Token Index: 919

Text #11

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1453188 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1371195 (Python Code)

Max Activating Token Index: 978

Text #13

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1580137 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1496470 (Python Code)

Max Activating Token Index: 948

Text #15

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6456. Min Act: -0.0000

Data Index: 198539 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1541645 (Python Code)

Max Activating Token Index: 644

Text #17

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1590609 (Python Code)

Max Activating Token Index: 990

Text #18

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1530117 (Python Code)

Max Activating Token Index: 867

Text #19

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1390572 (Python Code)

Max Activating Token Index: 401