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

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

Neuron 733 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.5446. Min Act: 0.0001

Data Index: 823846 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.5476. Min Act: -0.0001

Data Index: 1001928 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1240977 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4572. Min Act: -0.0000

Data Index: 996835 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4694. Min Act: -0.0001

Data Index: 751400 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4684. Min Act: -0.0000

Data Index: 734571 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1064558 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4697. Min Act: -0.0000

Data Index: 123157 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4663. Min Act: -0.0000

Data Index: 450889 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4669. Min Act: -0.0000

Data Index: 734513 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1345 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4466. Min Act: -0.0001

Data Index: 809361 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4588. Min Act: -0.0000

Data Index: 245373 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4568. Min Act: -0.0000

Data Index: 238449 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1083884 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4562. Min Act: -0.0000

Data Index: 837979 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1095209 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4490. Min Act: -0.0001

Data Index: 547137 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1242418 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4452. Min Act: -0.0000

Data Index: 276204 (C4 (Web Text))

Max Activating Token Index: 134