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

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

Neuron 640 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1952. Min Range: -1.1952

Max Act: 1.1952. Min Act: -0.0001

Data Index: 1263183 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.1952. Min Range: -1.1952

Max Act: 1.0527. Min Act: -0.0001

Data Index: 578446 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9725. Min Act: -0.0001

Data Index: 778623 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9590. Min Act: -0.0001

Data Index: 1112911 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9493. Min Act: -0.0001

Data Index: 678012 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9435. Min Act: -0.0001

Data Index: 235515 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9050. Min Act: -0.0001

Data Index: 1192808 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8819. Min Act: -0.0001

Data Index: 330913 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9135. Min Act: -0.0001

Data Index: 534928 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8057. Min Act: -0.0001

Data Index: 249092 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8072. Min Act: -0.0001

Data Index: 1266926 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8052. Min Act: -0.0001

Data Index: 733431 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8239. Min Act: -0.0001

Data Index: 1172662 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7873. Min Act: -0.0001

Data Index: 1048169 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7843. Min Act: -0.0001

Data Index: 891130 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8064. Min Act: -0.0001

Data Index: 1108179 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7805. Min Act: -0.0001

Data Index: 262659 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7766. Min Act: -0.0001

Data Index: 865900 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7642. Min Act: -0.0001

Data Index: 705746 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7687. Min Act: -0.0001

Data Index: 605491 (C4 (Web Text))

Max Activating Token Index: 94