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

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

Neuron 2017 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: 3.6589. Min Range: -3.6589

Max Act: 3.6589. Min Act: -0.1700

Data Index: 1629955 (Python Code)

Max Activating Token Index: 51

Text #1

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.4868. Min Act: -0.1700

Data Index: 1641391 (Python Code)

Max Activating Token Index: 123

Text #2

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.4341. Min Act: -0.1700

Data Index: 1378181 (Python Code)

Max Activating Token Index: 931

Text #3

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.4903. Min Act: -0.1700

Data Index: 1483519 (Python Code)

Max Activating Token Index: 401

Text #4

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.4435. Min Act: -0.1700

Data Index: 498567 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.4153. Min Act: -0.1700

Data Index: 96443 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.4077. Min Act: -0.1700

Data Index: 1469071 (Python Code)

Max Activating Token Index: 565

Text #7

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.4170. Min Act: -0.1700

Data Index: 1203127 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.4070. Min Act: -0.1700

Data Index: 1611422 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3812. Min Act: -0.1699

Data Index: 1462405 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3728. Min Act: -0.1700

Data Index: 1656091 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3811. Min Act: -0.1700

Data Index: 1551376 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3736. Min Act: -0.1700

Data Index: 1114099 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3998. Min Act: -0.1700

Data Index: 488064 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3531. Min Act: -0.1700

Data Index: 114225 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3667. Min Act: -0.1700

Data Index: 1397075 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3200. Min Act: -0.1700

Data Index: 1418338 (Python Code)

Max Activating Token Index: 894

Text #17

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3582. Min Act: -0.1700

Data Index: 1542970 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3656. Min Act: -0.1700

Data Index: 472656 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.3496. Min Act: -0.1700

Data Index: 1341063 (C4 (Web Text))

Max Activating Token Index: 694