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

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

Neuron 338 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: 4.3344. Min Range: -4.3344

Max Act: 4.3344. Min Act: -0.1700

Data Index: 905653 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 4.3344. Min Range: -4.3344

Max Act: 4.3006. Min Act: -0.1700

Data Index: 93525 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 4.3344. Min Range: -4.3344

Max Act: 4.1788. Min Act: -0.1700

Data Index: 124014 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 4.3344. Min Range: -4.3344

Max Act: 4.1919. Min Act: -0.1700

Data Index: 825326 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 4.3344. Min Range: -4.3344

Max Act: 4.1617. Min Act: -0.1700

Data Index: 483622 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 4.3344. Min Range: -4.3344

Max Act: 4.1090. Min Act: -0.1700

Data Index: 846302 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 4.3344. Min Range: -4.3344

Max Act: 4.0909. Min Act: -0.1700

Data Index: 773389 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 4.3344. Min Range: -4.3344

Max Act: 4.0368. Min Act: -0.1700

Data Index: 514556 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 4.3344. Min Range: -4.3344

Max Act: 4.0371. Min Act: -0.1700

Data Index: 996103 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 4.3344. Min Range: -4.3344

Max Act: 3.9998. Min Act: -0.1700

Data Index: 949874 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 4.3344. Min Range: -4.3344

Max Act: 4.0076. Min Act: -0.1700

Data Index: 166681 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 4.3344. Min Range: -4.3344

Max Act: 3.9911. Min Act: -0.1700

Data Index: 508860 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 4.3344. Min Range: -4.3344

Max Act: 3.9961. Min Act: -0.1700

Data Index: 147339 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 4.3344. Min Range: -4.3344

Max Act: 3.9919. Min Act: -0.1700

Data Index: 119434 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 4.3344. Min Range: -4.3344

Max Act: 3.9712. Min Act: -0.1700

Data Index: 1194862 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 4.3344. Min Range: -4.3344

Max Act: 3.9818. Min Act: -0.1700

Data Index: 730804 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 4.3344. Min Range: -4.3344

Max Act: 3.9936. Min Act: -0.1700

Data Index: 132178 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 4.3344. Min Range: -4.3344

Max Act: 3.9343. Min Act: -0.1700

Data Index: 393679 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 4.3344. Min Range: -4.3344

Max Act: 3.9314. Min Act: -0.1700

Data Index: 570704 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 4.3344. Min Range: -4.3344

Max Act: 3.9597. Min Act: -0.1700

Data Index: 191289 (C4 (Web Text))

Max Activating Token Index: 100