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

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

Neuron 1290 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.6877. Min Act: -0.1700

Data Index: 1244670 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.6095. Min Act: -0.1700

Data Index: 1341676 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.5782. Min Act: -0.1700

Data Index: 1328116 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.5782. Min Act: -0.1700

Data Index: 1035703 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.5468. Min Act: -0.1700

Data Index: 746903 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.5155. Min Act: -0.1700

Data Index: 394436 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4998. Min Act: -0.1700

Data Index: 606965 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4998. Min Act: -0.1700

Data Index: 613000 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4842. Min Act: -0.1700

Data Index: 1284187 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4998. Min Act: -0.1700

Data Index: 631214 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4685. Min Act: -0.1700

Data Index: 578190 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4685. Min Act: -0.1700

Data Index: 1219655 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4685. Min Act: -0.1700

Data Index: 1032139 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4685. Min Act: -0.1700

Data Index: 674805 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4372. Min Act: -0.1700

Data Index: 1187614 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4528. Min Act: -0.1700

Data Index: 1125436 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4528. Min Act: -0.1700

Data Index: 258243 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4528. Min Act: -0.1700

Data Index: 240737 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4215. Min Act: -0.1700

Data Index: 134033 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 3.6877. Min Range: -3.6877

Max Act: 3.4528. Min Act: -0.1700

Data Index: 1218602 (C4 (Web Text))

Max Activating Token Index: 128