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

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

Neuron 2966 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0458. Min Range: -1.0458

Max Act: 1.0458. Min Act: -0.0002

Data Index: 1246897 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9530. Min Act: -0.0001

Data Index: 1281544 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8355. Min Act: -0.0001

Data Index: 11938 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8358. Min Act: -0.0002

Data Index: 442181 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8403. Min Act: -0.0001

Data Index: 929047 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8118. Min Act: -0.0001

Data Index: 1191014 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7899. Min Act: -0.0002

Data Index: 231686 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7262. Min Act: -0.0001

Data Index: 610933 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7908. Min Act: -0.0002

Data Index: 663160 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7816. Min Act: -0.0001

Data Index: 1355392 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7713. Min Act: -0.0001

Data Index: 255938 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7387. Min Act: -0.0002

Data Index: 457884 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7257. Min Act: -0.0002

Data Index: 1137164 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.6789. Min Act: -0.0002

Data Index: 361531 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.6449. Min Act: -0.0001

Data Index: 989768 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.6355. Min Act: -0.0002

Data Index: 476370 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.6363. Min Act: -0.0002

Data Index: 184750 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.6678. Min Act: -0.0002

Data Index: 185538 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.6219. Min Act: -0.0002

Data Index: 970057 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.6050. Min Act: -0.0001

Data Index: 834737 (C4 (Web Text))

Max Activating Token Index: 245