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

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

Neuron 3728 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1249151 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.1006. Min Act: -0.0000

Data Index: 6098 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0981. Min Act: -0.0001

Data Index: 505113 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0956. Min Act: -0.0001

Data Index: 589505 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1103897 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1267600 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0935. Min Act: -0.0001

Data Index: 506328 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0923. Min Act: -0.0000

Data Index: 776524 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0878. Min Act: -0.0001

Data Index: 90043 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1218304 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0902. Min Act: -0.0001

Data Index: 131358 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0881. Min Act: -0.0001

Data Index: 874591 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0873. Min Act: -0.0001

Data Index: 854473 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1219545 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1252493 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0857. Min Act: -0.0001

Data Index: 522209 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0828. Min Act: -0.0001

Data Index: 942699 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0846. Min Act: -0.0001

Data Index: 92487 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0799. Min Act: -0.0000

Data Index: 545287 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0823. Min Act: -0.0001

Data Index: 680519 (C4 (Web Text))

Max Activating Token Index: 950