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

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

Neuron 1532 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0126. Min Range: -1.0126

Max Act: 1.0126. Min Act: -0.0001

Data Index: 32324 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.9007. Min Act: -0.0001

Data Index: 750570 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.8664. Min Act: -0.0001

Data Index: 1192079 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.9039. Min Act: -0.0001

Data Index: 785311 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.9340. Min Act: -0.0001

Data Index: 1154588 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.9281. Min Act: -0.0001

Data Index: 1006754 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.9276. Min Act: -0.0001

Data Index: 111232 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.8027. Min Act: -0.0001

Data Index: 450392 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.8517. Min Act: -0.0001

Data Index: 23116 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.8437. Min Act: -0.0001

Data Index: 97973 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.7935. Min Act: -0.0001

Data Index: 652747 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.8292. Min Act: -0.0001

Data Index: 300127 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.8243. Min Act: -0.0001

Data Index: 1123954 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.8696. Min Act: -0.0001

Data Index: 770833 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.7635. Min Act: -0.0001

Data Index: 284481 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6349. Min Act: -0.0001

Data Index: 145586 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.7668. Min Act: -0.0001

Data Index: 415695 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.7670. Min Act: -0.0001

Data Index: 282935 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6836. Min Act: -0.0001

Data Index: 244326 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.8554. Min Act: -0.0001

Data Index: 1230117 (C4 (Web Text))

Max Activating Token Index: 348