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

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

Neuron 2115 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: 0.6159. Min Range: -0.6159

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1466278 (Python Code)

Max Activating Token Index: 903

Text #1

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1641840 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5625. Min Act: -0.0001

Data Index: 1424016 (Python Code)

Max Activating Token Index: 114

Text #3

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5347. Min Act: 0.0000

Data Index: 1606835 (Python Code)

Max Activating Token Index: 498

Text #4

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4915. Min Act: -0.0000

Data Index: 586584 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1329191 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5085. Min Act: -0.0001

Data Index: 1430425 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4863. Min Act: -0.0000

Data Index: 559782 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4645. Min Act: -0.0001

Data Index: 256744 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4385. Min Act: -0.0000

Data Index: 559872 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4645. Min Act: -0.0001

Data Index: 705167 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4595. Min Act: -0.0001

Data Index: 727280 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4559. Min Act: -0.0000

Data Index: 905363 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4542. Min Act: 0.0000

Data Index: 609651 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4743. Min Act: -0.0000

Data Index: 456194 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4415. Min Act: -0.0001

Data Index: 850763 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1261727 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4170. Min Act: -0.0000

Data Index: 726274 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4122. Min Act: -0.0000

Data Index: 930416 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3990. Min Act: -0.0001

Data Index: 40640 (C4 (Web Text))

Max Activating Token Index: 532