Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1014 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.8676. Min Act: -0.1700

Data Index: 1079373 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.8051. Min Act: -0.1700

Data Index: 850126 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.7738. Min Act: -0.1700

Data Index: 80773 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.6799. Min Act: -0.1700

Data Index: 265104 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.6173. Min Act: -0.1700

Data Index: 120764 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.6173. Min Act: -0.1700

Data Index: 1191935 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.6173. Min Act: -0.1700

Data Index: 117455 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5860. Min Act: -0.1700

Data Index: 891881 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5860. Min Act: -0.1700

Data Index: 1347716 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5860. Min Act: -0.1700

Data Index: 1062509 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5860. Min Act: -0.1700

Data Index: 1155121 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5547. Min Act: -0.1700

Data Index: 5146 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5547. Min Act: -0.1700

Data Index: 936566 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5547. Min Act: -0.1700

Data Index: 656421 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5547. Min Act: -0.1700

Data Index: 1007743 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5547. Min Act: -0.1700

Data Index: 753655 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5233. Min Act: -0.1700

Data Index: 265655 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5233. Min Act: -0.1700

Data Index: 447880 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5233. Min Act: -0.1700

Data Index: 751271 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 3.8676. Min Range: -3.8676

Max Act: 3.5233. Min Act: -0.1700

Data Index: 133953 (C4 (Web Text))

Max Activating Token Index: 181