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

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

Neuron 4443 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: 1.7978. Min Range: -1.7978

Max Act: 1.7978. Min Act: -0.0000

Data Index: 284520 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5975. Min Act: -0.0000

Data Index: 1272261 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5641. Min Act: -0.0000

Data Index: 1079441 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5106. Min Act: -0.0000

Data Index: 1352673 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5865. Min Act: -0.0000

Data Index: 1233793 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4701. Min Act: -0.0000

Data Index: 282891 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4490. Min Act: -0.0000

Data Index: 513597 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5457. Min Act: -0.0000

Data Index: 1163080 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5449. Min Act: -0.0000

Data Index: 11566 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5088. Min Act: -0.0000

Data Index: 416431 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5149. Min Act: -0.0000

Data Index: 842972 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4278. Min Act: -0.0000

Data Index: 1158842 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5888. Min Act: -0.0000

Data Index: 901091 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.3922. Min Act: -0.0000

Data Index: 772844 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4153. Min Act: -0.0000

Data Index: 517814 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4007. Min Act: -0.0000

Data Index: 1296140 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4925. Min Act: -0.0000

Data Index: 287736 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4739. Min Act: -0.0000

Data Index: 520959 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4519. Min Act: -0.0000

Data Index: 186910 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4669. Min Act: -0.0000

Data Index: 327463 (C4 (Web Text))

Max Activating Token Index: 117