Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2561 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4931. Min Act: 0.0002

Data Index: 1175872 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4367. Min Act: -0.0001

Data Index: 538626 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3946. Min Act: 0.0002

Data Index: 1185753 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3988. Min Act: -0.0001

Data Index: 1221225 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3932. Min Act: -0.0001

Data Index: 365631 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3938. Min Act: 0.0002

Data Index: 13453 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4024. Min Act: -0.0001

Data Index: 1289901 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3598. Min Act: 0.0002

Data Index: 1347577 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3717. Min Act: 0.0001

Data Index: 833961 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3818. Min Act: 0.0002

Data Index: 133532 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3853. Min Act: -0.0001

Data Index: 1026358 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3562. Min Act: 0.0002

Data Index: 1014130 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1097914 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1242370 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3697. Min Act: -0.0001

Data Index: 824313 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3649. Min Act: -0.0001

Data Index: 631467 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3775. Min Act: -0.0001

Data Index: 128301 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3658. Min Act: -0.0001

Data Index: 1348982 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3615. Min Act: -0.0001

Data Index: 773973 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3595. Min Act: -0.0001

Data Index: 557475 (C4 (Web Text))

Max Activating Token Index: 694