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

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

Neuron 5440 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.6788. Min Act: -0.0001

Data Index: 492412 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.4748. Min Act: -0.0001

Data Index: 907149 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.0654. Min Act: -0.0001

Data Index: 810184 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.8344. Min Act: -0.0001

Data Index: 1257678 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.9395. Min Act: -0.0001

Data Index: 308809 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.7689. Min Act: -0.0001

Data Index: 1297997 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 4.6788. Min Range: -4.6788

Max Act: 2.3191. Min Act: -0.0001

Data Index: 1143934 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.6018. Min Act: -0.0001

Data Index: 227855 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.5677. Min Act: -0.0001

Data Index: 317258 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.4254. Min Act: -0.0001

Data Index: 499428 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.1383. Min Act: -0.0001

Data Index: 1049799 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.2410. Min Act: -0.0001

Data Index: 1040488 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.3812. Min Act: -0.0001

Data Index: 489904 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.3362. Min Act: -0.0001

Data Index: 124946 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.2989. Min Act: -0.0001

Data Index: 732346 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.1694. Min Act: -0.0001

Data Index: 1143411 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.4410. Min Act: -0.0001

Data Index: 1345922 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.2681. Min Act: -0.0001

Data Index: 472516 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.3611. Min Act: -0.0001

Data Index: 35229 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 4.6788. Min Range: -4.6788

Max Act: 3.3549. Min Act: -0.0001

Data Index: 1158672 (C4 (Web Text))

Max Activating Token Index: 548