Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 390 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0979. Min Act: -0.1700

Data Index: 525415 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.1137. Min Act: -0.1700

Data Index: 492316 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.1767. Min Act: -0.1700

Data Index: 1209622 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.1294. Min Act: -0.1700

Data Index: 226550 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0821. Min Act: -0.1700

Data Index: 663283 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0663. Min Act: -0.1700

Data Index: 365875 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0506. Min Act: -0.1700

Data Index: 834801 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0979. Min Act: -0.1700

Data Index: 872298 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0506. Min Act: -0.1700

Data Index: 673375 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0506. Min Act: -0.1700

Data Index: 300776 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0190. Min Act: -0.1700

Data Index: 1351447 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0190. Min Act: -0.1700

Data Index: 716450 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0663. Min Act: -0.1700

Data Index: 627115 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0506. Min Act: -0.1700

Data Index: 1170149 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0190. Min Act: -0.1700

Data Index: 1332500 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0506. Min Act: -0.1700

Data Index: 153066 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0190. Min Act: -0.1700

Data Index: 605943 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.9557. Min Act: -0.1700

Data Index: 92875 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.9557. Min Act: -0.1700

Data Index: 366130 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0663. Min Act: -0.1700

Data Index: 1065045 (C4 (Web Text))

Max Activating Token Index: 663