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

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

Neuron 1784 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: 3.2278. Min Range: -3.2278

Max Act: 3.2278. Min Act: -0.1700

Data Index: 1563500 (Python Code)

Max Activating Token Index: 286

Text #1

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.1092. Min Act: -0.1700

Data Index: 20605 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.0288. Min Act: -0.1700

Data Index: 839306 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.0110. Min Act: -0.1700

Data Index: 1628052 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9772. Min Act: -0.1700

Data Index: 1628312 (Python Code)

Max Activating Token Index: 275

Text #5

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9839. Min Act: -0.1700

Data Index: 218235 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9869. Min Act: -0.1700

Data Index: 174454 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9685. Min Act: -0.1700

Data Index: 617512 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9553. Min Act: -0.1700

Data Index: 1542836 (Python Code)

Max Activating Token Index: 179

Text #9

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9693. Min Act: -0.1700

Data Index: 1442582 (Python Code)

Max Activating Token Index: 600

Text #10

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9740. Min Act: -0.1700

Data Index: 1481218 (Python Code)

Max Activating Token Index: 664

Text #11

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9667. Min Act: -0.1700

Data Index: 1440035 (Python Code)

Max Activating Token Index: 269

Text #12

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9681. Min Act: -0.1700

Data Index: 1650907 (Python Code)

Max Activating Token Index: 79

Text #13

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9555. Min Act: -0.1700

Data Index: 1651231 (Python Code)

Max Activating Token Index: 775

Text #14

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9526. Min Act: -0.1700

Data Index: 1618767 (Python Code)

Max Activating Token Index: 1012

Text #15

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9443. Min Act: -0.1700

Data Index: 1402200 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9200. Min Act: -0.1700

Data Index: 1451362 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9146. Min Act: -0.1700

Data Index: 1441555 (Python Code)

Max Activating Token Index: 601

Text #18

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9071. Min Act: -0.1700

Data Index: 1446955 (Python Code)

Max Activating Token Index: 460

Text #19

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9168. Min Act: -0.1700

Data Index: 1513162 (Python Code)

Max Activating Token Index: 822