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

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

Neuron 1617 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: 3.1209. Min Range: -3.1209

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1633037 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 3.1209. Min Range: -3.1209

Max Act: 3.0707. Min Act: -0.1699

Data Index: 1033068 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 3.1209. Min Range: -3.1209

Max Act: 3.0706. Min Act: -0.1700

Data Index: 1653301 (Python Code)

Max Activating Token Index: 948

Text #3

Max Range: 3.1209. Min Range: -3.1209

Max Act: 3.0346. Min Act: -0.1700

Data Index: 1421822 (Python Code)

Max Activating Token Index: 912

Text #4

Max Range: 3.1209. Min Range: -3.1209

Max Act: 3.0319. Min Act: -0.1698

Data Index: 1412888 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 3.1209. Min Range: -3.1209

Max Act: 3.0196. Min Act: -0.1700

Data Index: 1501335 (Python Code)

Max Activating Token Index: 450

Text #6

Max Range: 3.1209. Min Range: -3.1209

Max Act: 3.0159. Min Act: -0.1698

Data Index: 957500 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 3.1209. Min Range: -3.1209

Max Act: 3.0290. Min Act: -0.1700

Data Index: 1617437 (Python Code)

Max Activating Token Index: 593

Text #8

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9927. Min Act: -0.1700

Data Index: 1641604 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9853. Min Act: -0.1700

Data Index: 1367471 (Python Code)

Max Activating Token Index: 787

Text #10

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9798. Min Act: -0.1700

Data Index: 1400352 (Python Code)

Max Activating Token Index: 748

Text #11

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9653. Min Act: -0.1510

Data Index: 548682 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9707. Min Act: -0.1699

Data Index: 1512155 (Python Code)

Max Activating Token Index: 837

Text #13

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9579. Min Act: -0.1696

Data Index: 1389003 (Python Code)

Max Activating Token Index: 897

Text #14

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9676. Min Act: -0.1700

Data Index: 1607781 (Python Code)

Max Activating Token Index: 201

Text #15

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9667. Min Act: -0.1700

Data Index: 1508903 (Python Code)

Max Activating Token Index: 591

Text #16

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9428. Min Act: -0.1700

Data Index: 1396678 (Python Code)

Max Activating Token Index: 632

Text #17

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9367. Min Act: -0.1700

Data Index: 866857 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9484. Min Act: -0.1700

Data Index: 1593591 (Python Code)

Max Activating Token Index: 890

Text #19

Max Range: 3.1209. Min Range: -3.1209

Max Act: 2.9473. Min Act: -0.1700

Data Index: 1474663 (Python Code)

Max Activating Token Index: 1012