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

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

Neuron 3618 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.2043. Min Act: -0.0001

Data Index: 481062 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9658. Min Act: -0.0001

Data Index: 848943 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9176. Min Act: -0.0001

Data Index: 1034103 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9587. Min Act: -0.0001

Data Index: 953033 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.8837. Min Act: -0.0001

Data Index: 1267546 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7855. Min Act: -0.0001

Data Index: 466494 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.8639. Min Act: -0.0001

Data Index: 820148 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7845. Min Act: -0.0001

Data Index: 733089 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.8105. Min Act: -0.0001

Data Index: 920604 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7885. Min Act: -0.0001

Data Index: 868273 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7889. Min Act: -0.0001

Data Index: 1113958 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7718. Min Act: -0.0001

Data Index: 103602 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7680. Min Act: -0.0001

Data Index: 248849 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7395. Min Act: -0.0001

Data Index: 500105 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.6539. Min Act: -0.0001

Data Index: 904900 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7908. Min Act: -0.0001

Data Index: 867942 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7070. Min Act: -0.0001

Data Index: 486132 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7609. Min Act: -0.0001

Data Index: 890949 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7580. Min Act: -0.0001

Data Index: 1196312 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7733. Min Act: -0.0001

Data Index: 1155789 (C4 (Web Text))

Max Activating Token Index: 141