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

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

Neuron 947 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.4729. Min Act: -0.1700

Data Index: 941752 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.4102. Min Act: -0.1700

Data Index: 1086095 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2846. Min Act: -0.1700

Data Index: 1279197 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2532. Min Act: -0.1700

Data Index: 1257498 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2846. Min Act: -0.1700

Data Index: 756398 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2217. Min Act: -0.1700

Data Index: 158637 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2060. Min Act: -0.1700

Data Index: 607952 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1745. Min Act: -0.1700

Data Index: 949109 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1588. Min Act: -0.1700

Data Index: 689336 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1745. Min Act: -0.1700

Data Index: 307497 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1115. Min Act: -0.1700

Data Index: 197243 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1273. Min Act: -0.1700

Data Index: 826395 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1273. Min Act: -0.1700

Data Index: 1247693 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1273. Min Act: -0.1700

Data Index: 917662 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1115. Min Act: -0.1700

Data Index: 1241798 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1115. Min Act: -0.1700

Data Index: 686 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1115. Min Act: -0.1700

Data Index: 507320 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1273. Min Act: -0.1700

Data Index: 683848 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.0958. Min Act: -0.1700

Data Index: 940823 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1115. Min Act: -0.1700

Data Index: 474637 (C4 (Web Text))

Max Activating Token Index: 1023