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

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

Neuron 882 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3161. Min Range: -5.3161

Max Act: 5.3161. Min Act: -0.1700

Data Index: 455849 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 5.3161. Min Range: -5.3161

Max Act: 5.1911. Min Act: -0.1700

Data Index: 1278016 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 5.3161. Min Range: -5.3161

Max Act: 5.0661. Min Act: -0.1700

Data Index: 84974 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.9098. Min Act: -0.1700

Data Index: 1163443 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.9411. Min Act: -0.1700

Data Index: 1290726 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.8473. Min Act: -0.1700

Data Index: 345537 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.9411. Min Act: -0.1700

Data Index: 203607 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.8161. Min Act: -0.1700

Data Index: 27858 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.7536. Min Act: -0.1700

Data Index: 788312 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.7536. Min Act: -0.1700

Data Index: 889426 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.7848. Min Act: -0.1700

Data Index: 1049691 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.7223. Min Act: -0.1700

Data Index: 889510 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.7848. Min Act: -0.1700

Data Index: 829052 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.7848. Min Act: -0.1700

Data Index: 341176 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.7848. Min Act: -0.1700

Data Index: 1085940 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.7223. Min Act: -0.1700

Data Index: 1247774 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.6911. Min Act: -0.1700

Data Index: 651934 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.7223. Min Act: -0.1700

Data Index: 463457 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.6911. Min Act: -0.1700

Data Index: 925653 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 5.3161. Min Range: -5.3161

Max Act: 4.6598. Min Act: -0.1700

Data Index: 791167 (C4 (Web Text))

Max Activating Token Index: 333