Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1419 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.2910. Min Act: -0.1700

Data Index: 1648293 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.1809. Min Act: -0.1700

Data Index: 1580928 (Python Code)

Max Activating Token Index: 578

Text #2

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.1494. Min Act: -0.1700

Data Index: 1464104 (Python Code)

Max Activating Token Index: 393

Text #3

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.1179. Min Act: -0.1700

Data Index: 1550084 (Python Code)

Max Activating Token Index: 398

Text #4

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.1337. Min Act: -0.1700

Data Index: 1640700 (Python Code)

Max Activating Token Index: 61

Text #5

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.0706. Min Act: -0.1700

Data Index: 1578220 (Python Code)

Max Activating Token Index: 969

Text #6

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.0548. Min Act: -0.1700

Data Index: 1413302 (Python Code)

Max Activating Token Index: 837

Text #7

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.0390. Min Act: -0.1700

Data Index: 1487500 (Python Code)

Max Activating Token Index: 231

Text #8

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.0232. Min Act: -0.1700

Data Index: 1453734 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.0232. Min Act: -0.1700

Data Index: 1548900 (Python Code)

Max Activating Token Index: 203

Text #10

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.0074. Min Act: -0.1700

Data Index: 1644765 (Python Code)

Max Activating Token Index: 981

Text #11

Max Range: 3.2910. Min Range: -3.2910

Max Act: 3.0074. Min Act: -0.1700

Data Index: 1618315 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 3.2910. Min Range: -3.2910

Max Act: 2.9600. Min Act: -0.1700

Data Index: 1513140 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 3.2910. Min Range: -3.2910

Max Act: 2.9441. Min Act: -0.1700

Data Index: 1608418 (Python Code)

Max Activating Token Index: 489

Text #14

Max Range: 3.2910. Min Range: -3.2910

Max Act: 2.8966. Min Act: -0.1700

Data Index: 1547140 (Python Code)

Max Activating Token Index: 144

Text #15

Max Range: 3.2910. Min Range: -3.2910

Max Act: 2.8807. Min Act: -0.1700

Data Index: 1656727 (Python Code)

Max Activating Token Index: 562

Text #16

Max Range: 3.2910. Min Range: -3.2910

Max Act: 2.8648. Min Act: -0.1700

Data Index: 1409115 (Python Code)

Max Activating Token Index: 498

Text #17

Max Range: 3.2910. Min Range: -3.2910

Max Act: 2.8489. Min Act: -0.1700

Data Index: 1568819 (Python Code)

Max Activating Token Index: 940

Text #18

Max Range: 3.2910. Min Range: -3.2910

Max Act: 2.8648. Min Act: -0.1700

Data Index: 1571821 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 3.2910. Min Range: -3.2910

Max Act: 2.8489. Min Act: -0.1700

Data Index: 885667 (C4 (Web Text))

Max Activating Token Index: 486