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

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

Neuron 2043 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0391. Min Range: -7.0391

Max Act: 7.0391. Min Act: -0.1700

Data Index: 451819 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5079. Min Act: -0.1700

Data Index: 973633 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5391. Min Act: -0.1700

Data Index: 1240377 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.6016. Min Act: -0.1700

Data Index: 1311734 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5079. Min Act: -0.1700

Data Index: 661453 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5704. Min Act: -0.1700

Data Index: 549447 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5391. Min Act: -0.1700

Data Index: 872923 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4766. Min Act: -0.1700

Data Index: 158771 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5391. Min Act: -0.1700

Data Index: 191241 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4766. Min Act: -0.1700

Data Index: 1045844 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5391. Min Act: -0.1700

Data Index: 1060140 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5079. Min Act: -0.1700

Data Index: 1137039 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4141. Min Act: -0.1700

Data Index: 576191 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5704. Min Act: -0.1700

Data Index: 1124043 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4766. Min Act: -0.1700

Data Index: 15700 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4141. Min Act: -0.1700

Data Index: 823159 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4766. Min Act: -0.1700

Data Index: 205919 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4766. Min Act: -0.1700

Data Index: 500913 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4454. Min Act: -0.1700

Data Index: 1058890 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5079. Min Act: -0.1700

Data Index: 850502 (C4 (Web Text))

Max Activating Token Index: 592