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

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

Neuron 3635 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.7967. Min Act: -0.0001

Data Index: 1108376 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.5390. Min Act: -0.0001

Data Index: 1081088 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.4311. Min Act: -0.0001

Data Index: 1011262 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.3762. Min Act: -0.0002

Data Index: 210386 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.4095. Min Act: -0.0002

Data Index: 1074102 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.3192. Min Act: -0.0001

Data Index: 56579 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.1853. Min Act: -0.0002

Data Index: 1150358 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.3774. Min Act: -0.0001

Data Index: 214631 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.2162. Min Act: -0.0002

Data Index: 303157 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.1657. Min Act: -0.0001

Data Index: 1038740 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.0901. Min Act: -0.0002

Data Index: 657427 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.2093. Min Act: -0.0002

Data Index: 748373 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.2398. Min Act: -0.0001

Data Index: 726373 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.1575. Min Act: -0.0001

Data Index: 192389 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.0743. Min Act: -0.0001

Data Index: 503005 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.1132. Min Act: -0.0001

Data Index: 388941 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.2082. Min Act: -0.0001

Data Index: 6537 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.1345. Min Act: -0.0001

Data Index: 1163238 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.1715. Min Act: -0.0001

Data Index: 653649 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.1395. Min Act: -0.0001

Data Index: 489146 (C4 (Web Text))

Max Activating Token Index: 101