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

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

Neuron 979 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: 3.8087. Min Range: -3.8087

Max Act: 3.8087. Min Act: -0.1700

Data Index: 210318 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.7461. Min Act: -0.1700

Data Index: 830086 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.6835. Min Act: -0.1700

Data Index: 490752 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.5270. Min Act: -0.1700

Data Index: 680039 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4800. Min Act: -0.1700

Data Index: 266204 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4643. Min Act: -0.1700

Data Index: 425419 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4486. Min Act: -0.1700

Data Index: 602834 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.5113. Min Act: -0.1700

Data Index: 532874 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4800. Min Act: -0.1700

Data Index: 1060195 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4800. Min Act: -0.1700

Data Index: 1097340 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4643. Min Act: -0.1700

Data Index: 280033 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4643. Min Act: -0.1700

Data Index: 307343 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4643. Min Act: -0.1700

Data Index: 797445 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4643. Min Act: -0.1700

Data Index: 960597 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4486. Min Act: -0.1700

Data Index: 1320071 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4800. Min Act: -0.1700

Data Index: 405928 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4486. Min Act: -0.1700

Data Index: 1151438 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4486. Min Act: -0.1700

Data Index: 975322 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4643. Min Act: -0.1700

Data Index: 615619 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 3.8087. Min Range: -3.8087

Max Act: 3.4643. Min Act: -0.1700

Data Index: 12282 (C4 (Web Text))

Max Activating Token Index: 158