Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1292 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.3383. Min Act: -0.1700

Data Index: 873121 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1969. Min Act: -0.1700

Data Index: 1359197 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1812. Min Act: -0.1700

Data Index: 1106949 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1812. Min Act: -0.1700

Data Index: 1147660 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1339. Min Act: -0.1700

Data Index: 178321 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1497. Min Act: -0.1700

Data Index: 1135326 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1182. Min Act: -0.1700

Data Index: 114445 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1339. Min Act: -0.1700

Data Index: 879097 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1024. Min Act: -0.1700

Data Index: 544091 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.0708. Min Act: -0.1700

Data Index: 1129874 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1024. Min Act: -0.1700

Data Index: 676221 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1024. Min Act: -0.1700

Data Index: 313722 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.1024. Min Act: -0.1700

Data Index: 296575 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.0708. Min Act: -0.1700

Data Index: 459240 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.0866. Min Act: -0.1700

Data Index: 632625 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.0551. Min Act: -0.1700

Data Index: 519977 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.0708. Min Act: -0.1700

Data Index: 895616 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.0551. Min Act: -0.1700

Data Index: 1253326 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.0393. Min Act: -0.1700

Data Index: 971529 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 3.3383. Min Range: -3.3383

Max Act: 3.0708. Min Act: -0.1700

Data Index: 269643 (C4 (Web Text))

Max Activating Token Index: 59