Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 370 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.8993. Min Act: -0.1700

Data Index: 734038 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.8089. Min Act: -0.1700

Data Index: 1025069 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.6959. Min Act: -0.1700

Data Index: 1157055 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.6741. Min Act: -0.1700

Data Index: 673564 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.6518. Min Act: -0.1700

Data Index: 932236 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.6405. Min Act: -0.1700

Data Index: 874338 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.5715. Min Act: -0.1700

Data Index: 191433 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.5391. Min Act: -0.1700

Data Index: 1113752 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.5098. Min Act: -0.1700

Data Index: 890717 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.5015. Min Act: -0.1700

Data Index: 49669 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.5075. Min Act: -0.1700

Data Index: 354781 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.4730. Min Act: -0.1700

Data Index: 246328 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.4468. Min Act: -0.1700

Data Index: 1252311 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.4287. Min Act: -0.1700

Data Index: 1322663 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.4102. Min Act: -0.1700

Data Index: 226211 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.4291. Min Act: -0.1700

Data Index: 675325 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.3724. Min Act: -0.1700

Data Index: 377495 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.3841. Min Act: -0.1700

Data Index: 606814 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.3667. Min Act: -0.1700

Data Index: 221893 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 4.8993. Min Range: -4.8993

Max Act: 4.3834. Min Act: -0.1700

Data Index: 589428 (C4 (Web Text))

Max Activating Token Index: 202