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

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

Neuron 419 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4746. Min Act: -0.0001

Data Index: 311533 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4279. Min Act: -0.0001

Data Index: 517001 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4599. Min Act: -0.0001

Data Index: 814879 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4557. Min Act: -0.0001

Data Index: 457416 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4348. Min Act: -0.0001

Data Index: 628047 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1137174 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4060. Min Act: -0.0001

Data Index: 216548 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1349767 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4276. Min Act: -0.0001

Data Index: 927121 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3863. Min Act: -0.0001

Data Index: 522012 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3902. Min Act: -0.0000

Data Index: 334409 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3890. Min Act: -0.0001

Data Index: 572999 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4086. Min Act: -0.0000

Data Index: 947567 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3475. Min Act: -0.0001

Data Index: 276276 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1356471 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3799. Min Act: -0.0000

Data Index: 893069 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3812. Min Act: -0.0001

Data Index: 273692 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3754. Min Act: -0.0000

Data Index: 791355 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3466. Min Act: -0.0001

Data Index: 870055 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1162423 (C4 (Web Text))

Max Activating Token Index: 920