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

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

Neuron 497 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6104. Min Range: -4.6104

Max Act: 4.6104. Min Act: -0.0000

Data Index: 1328352 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 4.6104. Min Range: -4.6104

Max Act: 3.4202. Min Act: -0.0000

Data Index: 509959 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.9232. Min Act: -0.0000

Data Index: 1198998 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.8475. Min Act: -0.0000

Data Index: 1223374 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.8325. Min Act: -0.0000

Data Index: 784808 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.7984. Min Act: -0.0000

Data Index: 975773 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.7616. Min Act: -0.0000

Data Index: 972264 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.7315. Min Act: -0.0000

Data Index: 156013 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.5545. Min Act: -0.0000

Data Index: 1203422 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.6877. Min Act: -0.0000

Data Index: 1023112 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.6728. Min Act: -0.0000

Data Index: 1143212 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.6487. Min Act: -0.0000

Data Index: 272690 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.6161. Min Act: -0.0000

Data Index: 595942 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.7608. Min Act: -0.0000

Data Index: 2632 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.5930. Min Act: -0.0000

Data Index: 755695 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.5611. Min Act: -0.0000

Data Index: 751276 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.5702. Min Act: -0.0000

Data Index: 1356173 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.5503. Min Act: -0.0000

Data Index: 694625 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.4887. Min Act: -0.0000

Data Index: 282314 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 4.6104. Min Range: -4.6104

Max Act: 2.4409. Min Act: -0.0000

Data Index: 739086 (C4 (Web Text))

Max Activating Token Index: 782