Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1664 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1937. Min Range: -3.1937

Max Act: 3.1937. Min Act: -0.1700

Data Index: 1269370 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 3.1937. Min Range: -3.1937

Max Act: 3.0834. Min Act: -0.1700

Data Index: 1139845 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 3.1937. Min Range: -3.1937

Max Act: 3.0203. Min Act: -0.1700

Data Index: 387984 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 3.1937. Min Range: -3.1937

Max Act: 3.0045. Min Act: -0.1700

Data Index: 408815 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 3.1937. Min Range: -3.1937

Max Act: 3.0045. Min Act: -0.1700

Data Index: 100608 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9729. Min Act: -0.1700

Data Index: 155015 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9729. Min Act: -0.1700

Data Index: 320508 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9412. Min Act: -0.1700

Data Index: 1289306 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9729. Min Act: -0.1700

Data Index: 538964 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9412. Min Act: -0.1700

Data Index: 463005 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8778. Min Act: -0.1700

Data Index: 1154763 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9095. Min Act: -0.1700

Data Index: 1192317 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9095. Min Act: -0.1700

Data Index: 166379 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8778. Min Act: -0.1700

Data Index: 367138 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9095. Min Act: -0.1700

Data Index: 312134 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8778. Min Act: -0.1700

Data Index: 837657 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8778. Min Act: -0.1700

Data Index: 909042 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8460. Min Act: -0.1700

Data Index: 697428 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8778. Min Act: -0.1700

Data Index: 260550 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8778. Min Act: -0.1700

Data Index: 252209 (C4 (Web Text))

Max Activating Token Index: 110