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

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

Neuron 773 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.6156. Min Act: -0.1700

Data Index: 1296274 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.5218. Min Act: -0.1700

Data Index: 904152 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.4281. Min Act: -0.1700

Data Index: 227898 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.4906. Min Act: -0.1700

Data Index: 818982 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.4906. Min Act: -0.1700

Data Index: 1352684 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.4906. Min Act: -0.1700

Data Index: 186316 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.4281. Min Act: -0.1700

Data Index: 952255 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.4281. Min Act: -0.1700

Data Index: 814115 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.4281. Min Act: -0.1700

Data Index: 1073072 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.4281. Min Act: -0.1700

Data Index: 1234076 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.4281. Min Act: -0.1700

Data Index: 1059067 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.4281. Min Act: -0.1700

Data Index: 76214 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.3343. Min Act: -0.1700

Data Index: 1254909 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.3343. Min Act: -0.1700

Data Index: 286744 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.3656. Min Act: -0.1700

Data Index: 849250 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.3343. Min Act: -0.1700

Data Index: 25964 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.3656. Min Act: -0.1700

Data Index: 271438 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.3656. Min Act: -0.1700

Data Index: 1177008 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.3031. Min Act: -0.1700

Data Index: 1351641 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 5.6156. Min Range: -5.6156

Max Act: 5.3343. Min Act: -0.1700

Data Index: 1325399 (C4 (Web Text))

Max Activating Token Index: 401