Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 960 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1008729 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6972. Min Act: -0.0000

Data Index: 37217 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6609. Min Act: -0.0000

Data Index: 618567 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6512. Min Act: -0.0000

Data Index: 377000 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1284029 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5974. Min Act: -0.0000

Data Index: 289888 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5689. Min Act: -0.0000

Data Index: 374171 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1309426 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1166190 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5929. Min Act: -0.0000

Data Index: 75456 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1169235 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1083209 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5786. Min Act: -0.0000

Data Index: 480899 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5725. Min Act: -0.0000

Data Index: 645767 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5643. Min Act: -0.0000

Data Index: 267892 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5796. Min Act: -0.0000

Data Index: 139047 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5773. Min Act: -0.0000

Data Index: 89555 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5790. Min Act: -0.0000

Data Index: 264924 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1079809 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5722. Min Act: -0.0000

Data Index: 1185917 (C4 (Web Text))

Max Activating Token Index: 58