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

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

Neuron 315 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: 3.9537. Min Range: -3.9537

Max Act: 3.9537. Min Act: -0.1700

Data Index: 997000 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.9172. Min Act: -0.1700

Data Index: 1243546 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.7375. Min Act: -0.1554

Data Index: 759390 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.6975. Min Act: -0.1699

Data Index: 782135 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.6543. Min Act: -0.1700

Data Index: 1478413 (Python Code)

Max Activating Token Index: 90

Text #5

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.6148. Min Act: -0.1502

Data Index: 1380918 (Python Code)

Max Activating Token Index: 174

Text #6

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.6013. Min Act: -0.1695

Data Index: 1606838 (Python Code)

Max Activating Token Index: 385

Text #7

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.6084. Min Act: -0.1627

Data Index: 1617856 (Python Code)

Max Activating Token Index: 220

Text #8

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.6074. Min Act: -0.1652

Data Index: 1428845 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.6083. Min Act: -0.1695

Data Index: 622048 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.5679. Min Act: -0.1689

Data Index: 1508448 (Python Code)

Max Activating Token Index: 702

Text #11

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.5504. Min Act: -0.1697

Data Index: 1384811 (Python Code)

Max Activating Token Index: 157

Text #12

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.5285. Min Act: -0.1604

Data Index: 1597510 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.5185. Min Act: -0.1602

Data Index: 37138 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.5304. Min Act: -0.1502

Data Index: 1576676 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.5218. Min Act: -0.1502

Data Index: 1415535 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.5110. Min Act: -0.1672

Data Index: 51637 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.4897. Min Act: -0.1502

Data Index: 1425684 (Python Code)

Max Activating Token Index: 420

Text #18

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.5081. Min Act: -0.1699

Data Index: 1443193 (Python Code)

Max Activating Token Index: 825

Text #19

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.5156. Min Act: -0.1684

Data Index: 1378721 (Python Code)

Max Activating Token Index: 219