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

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

Neuron 1382 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: 3.5139. Min Range: -3.5139

Max Act: 3.5139. Min Act: -0.1700

Data Index: 423922 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.4825. Min Act: -0.1700

Data Index: 837853 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.4198. Min Act: -0.1700

Data Index: 855057 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.5139. Min Act: -0.1700

Data Index: 288769 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3885. Min Act: -0.1700

Data Index: 1357687 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3571. Min Act: -0.1700

Data Index: 842936 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3885. Min Act: -0.1700

Data Index: 486715 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3571. Min Act: -0.1700

Data Index: 986943 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3571. Min Act: -0.1700

Data Index: 102398 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3885. Min Act: -0.1700

Data Index: 768308 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3571. Min Act: -0.1700

Data Index: 253362 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3571. Min Act: -0.1700

Data Index: 182001 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3257. Min Act: -0.1700

Data Index: 216527 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3257. Min Act: -0.1700

Data Index: 512660 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3257. Min Act: -0.1700

Data Index: 351632 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3571. Min Act: -0.1700

Data Index: 796102 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3257. Min Act: -0.1700

Data Index: 884988 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.2943. Min Act: -0.1700

Data Index: 731161 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.3257. Min Act: -0.1700

Data Index: 850085 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 3.5139. Min Range: -3.5139

Max Act: 3.2943. Min Act: -0.1700

Data Index: 414362 (C4 (Web Text))

Max Activating Token Index: 857