Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 631 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1359. Min Act: -0.0004

Data Index: 53483 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1107. Min Act: -0.0003

Data Index: 1013931 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1124. Min Act: -0.0003

Data Index: 239655 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1023. Min Act: -0.0003

Data Index: 281251 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0997. Min Act: -0.0004

Data Index: 1239460 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1069. Min Act: -0.0003

Data Index: 1205323 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0991. Min Act: -0.0003

Data Index: 160379 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0978. Min Act: -0.0003

Data Index: 777843 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0941. Min Act: -0.0004

Data Index: 747412 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0937. Min Act: -0.0004

Data Index: 1067407 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0933. Min Act: -0.0003

Data Index: 915511 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0928. Min Act: -0.0004

Data Index: 128986 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0921. Min Act: -0.0003

Data Index: 974431 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0893. Min Act: -0.0003

Data Index: 530358 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0920. Min Act: -0.0003

Data Index: 196126 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0913. Min Act: -0.0003

Data Index: 1340906 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0939. Min Act: -0.0003

Data Index: 7599 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0926. Min Act: -0.0004

Data Index: 1276455 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0861. Min Act: -0.0003

Data Index: 165218 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1022943 (C4 (Web Text))

Max Activating Token Index: 134