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

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

Neuron 2244 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.7197. Min Act: -0.0001

Data Index: 373805 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6917. Min Act: -0.0001

Data Index: 1202538 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6293. Min Act: -0.0001

Data Index: 329733 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6120. Min Act: -0.0001

Data Index: 219665 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6589. Min Act: -0.0001

Data Index: 908219 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5986. Min Act: -0.0001

Data Index: 1241381 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6675. Min Act: -0.0001

Data Index: 1134800 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5562. Min Act: -0.0001

Data Index: 295368 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6753. Min Act: -0.0001

Data Index: 420521 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6230. Min Act: -0.0001

Data Index: 292422 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5602. Min Act: -0.0001

Data Index: 940845 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6793. Min Act: -0.0001

Data Index: 1208064 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5807. Min Act: -0.0001

Data Index: 514536 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5651. Min Act: -0.0001

Data Index: 346076 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5881. Min Act: -0.0001

Data Index: 704392 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6032. Min Act: -0.0001

Data Index: 888924 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5957. Min Act: -0.0001

Data Index: 170319 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4727. Min Act: -0.0001

Data Index: 322959 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5594. Min Act: -0.0001

Data Index: 1263568 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6146. Min Act: -0.0001

Data Index: 1359103 (C4 (Web Text))

Max Activating Token Index: 4