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

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

Neuron 1608 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7816. Min Act: -0.1700

Data Index: 705584 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7347. Min Act: -0.1700

Data Index: 519106 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7347. Min Act: -0.1700

Data Index: 277261 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6565. Min Act: -0.1700

Data Index: 379086 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6721. Min Act: -0.1700

Data Index: 1044077 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6878. Min Act: -0.1700

Data Index: 992973 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6252. Min Act: -0.1700

Data Index: 1103019 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6721. Min Act: -0.1700

Data Index: 312742 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6565. Min Act: -0.1700

Data Index: 813377 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6721. Min Act: -0.1700

Data Index: 910570 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6095. Min Act: -0.1700

Data Index: 1355476 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6095. Min Act: -0.1700

Data Index: 474694 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6252. Min Act: -0.1700

Data Index: 252786 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6252. Min Act: -0.1700

Data Index: 1096665 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5469. Min Act: -0.1700

Data Index: 1132479 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5782. Min Act: -0.1700

Data Index: 734113 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5939. Min Act: -0.1700

Data Index: 259290 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5782. Min Act: -0.1700

Data Index: 1144915 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6095. Min Act: -0.1700

Data Index: 94783 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5939. Min Act: -0.1700

Data Index: 310070 (C4 (Web Text))

Max Activating Token Index: 127